CN117540975A - Machine room equipment on-shelf recommendation method, system, device and storage medium - Google Patents
Machine room equipment on-shelf recommendation method, system, device and storage medium Download PDFInfo
- Publication number
- CN117540975A CN117540975A CN202311465202.9A CN202311465202A CN117540975A CN 117540975 A CN117540975 A CN 117540975A CN 202311465202 A CN202311465202 A CN 202311465202A CN 117540975 A CN117540975 A CN 117540975A
- Authority
- CN
- China
- Prior art keywords
- equipment
- shelf
- information
- data
- scheme
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000004088 simulation Methods 0.000 claims abstract description 70
- 238000012549 training Methods 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 26
- 230000001360 synchronised effect Effects 0.000 claims description 18
- 230000005611 electricity Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims 1
- 238000004891 communication Methods 0.000 abstract description 8
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 12
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 10
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000013439 planning Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000001939 inductive effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000013440 design planning Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machine room equipment on-shelf recommendation method, a system, a device and a storage medium, wherein service information is determined according to acquired service requirements, resource information and dynamic ring information are acquired through communication with a resource system and dynamic ring equipment, first data information is acquired according to the service information and the resource information, the first data information and the dynamic ring information are input into a trained prediction model to obtain a plurality of first schemes, the plurality of first schemes are scored according to a preset scoring system to obtain a plurality of comprehensive influence scores, a simulation scheme set is determined according to the plurality of comprehensive influence scores and a first preset threshold value, an external input instruction is received, an on-shelf scheme is determined from the simulation scheme set according to the external input instruction, and the on-shelf scheme is sent to the resource system to perform a preemption operation to generate a pre-acceptance label; the embodiment of the invention can improve the utilization rate of machine room resources and the rationality and applicability of the on-shelf scheme. The embodiment of the invention can be widely applied to the technical field of information processing.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method, a system, an apparatus, and a storage medium for recommending machine room equipment to be put on shelf.
Background
In the operation management process of the machine room of the communication operator, the resource management and the design planning of the machine room are very important, wherein the resource management of the machine room mainly carries out reasonable planning and design on the on-shelf position of equipment in the machine room, and each resource of the machine room is utilized to the maximum extent, so that the maximum benefit is obtained.
In practical application, resource information of a machine room is obtained through a resource management platform, and if the space and power of the machine room can meet service requirements, the machine room is allocated to equipment for putting on shelf; when the equipment on the upper frame of the cabinet is too much, the load on the cabinet is too heavy, and the cabinet can be damaged; and the equipment on the rack is too much, and the heat generated during the operation of the equipment makes the temperature of the machine room too high, so that the equipment in the machine room cannot work with rated power, and resource waste is caused.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide a method, a system, a device, and a storage medium for recommending a machine room equipment on-shelf, and combine multiple factors to recommend a scheme, so as to improve the resource utilization rate and improve the applicability.
On the one hand, the embodiment of the invention provides a method for recommending the equipment in a machine room to be put on shelf, which comprises the following steps:
acquiring service information, resource information and dynamic ring information; the service information comprises U-bit space information of the on-shelf equipment, rated power of the on-shelf equipment, user names and density of the on-shelf equipment; the resource information comprises a standard load value, a U-bit space and bearing information of the machine room cabinet; the movable ring information comprises air conditioner refrigerating capacity, temperature, humidity and electricity load of a machine room;
inputting the service information, the resource information and the dynamic ring information into a trained prediction model to obtain a plurality of first schemes;
sequentially scoring the first schemes according to a preset scoring system to obtain a plurality of comprehensive influence scores;
determining a simulation scheme set according to the comprehensive influence scores and a first preset threshold;
and acquiring an external instruction, determining an on-shelf scheme according to the external instruction and the simulation scheme set, and sending the on-shelf scheme to a resource system to execute a preemption operation so as to generate a pre-acceptance label.
Optionally, scoring the first scheme according to a preset scoring system to obtain a comprehensive influence score, which specifically includes:
Determining a first data set and a weight corresponding to the first data set according to a first scheme; the first data set comprises U-bit space data of the equipment cabinet after equipment is put on shelf, environment temperature data of the equipment cabinet after equipment is put on shelf and power load data of the equipment cabinet after equipment is put on shelf;
sequentially reading second data from the first data set, and matching the second data with the preset scoring system to obtain an influence score of the second data; the second data represents any one of U-bit space data of the equipment rack after the equipment is put on shelf, environment temperature data of the equipment rack after the equipment is put on shelf and power load data of the equipment rack after the equipment is put on shelf;
and carrying out weighted summation on the influence scores of the second data according to the weights to obtain comprehensive influence scores.
Optionally, the determining a simulation scheme set according to the plurality of comprehensive impact scores and a first preset threshold specifically includes:
sequentially comparing a plurality of comprehensive influence scores with a first preset threshold value, and taking the first scheme corresponding to the comprehensive influence score as a simulation scheme if the comprehensive influence score is larger than or equal to the first preset threshold value;
A simulation scheme set is determined from a number of the simulation schemes.
Optionally, the method further comprises:
acquiring a preset synchronization period, and carrying out real-time synchronization on the service information, the resource information and the moving ring information according to the preset synchronization period;
and sending the synchronized service information, the resource information and the moving ring information to a resource database for storage, and sending the synchronized service information, the synchronized resource information and the moving ring information to a mobile terminal for updating front-end data.
Optionally, the method further comprises:
sending the virtual preloading to a digital twin platform according to the racking scheme to generate a virtual 3D visual model of the racking scheme; the third data set comprises the overhead equipment U-bit space information, the overhead equipment power information, the overhead density information, the machine room cabinet bearing information and the machine room cabinet environment information.
Optionally, the training process of the prediction model is as follows:
determining a sample data set according to a plurality of test schemes, and dividing and screening the sample data set according to preset proportions to obtain a training data set and a test data set; the test data set comprises the U-bit space utilization rate of the equipment, the power consumption data of the equipment and the environment data of the equipment;
Inputting the training data set into a first model to obtain a first result;
calculating prediction accuracy according to the first result, and performing parameter adjustment on the first model according to the prediction accuracy and a second preset threshold until the prediction accuracy meets the second preset threshold to obtain a second model;
inputting the test data set into the second model to obtain a second result; calculating a performance value according to the test data set and the second result, and taking the second model as a prediction model if the performance value reaches a third preset threshold; wherein the performance value comprises a root mean square error and an average absolute error.
Optionally, the first model includes a third model and a fourth model, and the training dataset is input into the first model to obtain a first result, which specifically includes:
inputting the training data set into a third model for prediction to obtain a first prediction result; wherein the first predictive result characterizes an on-shelf simulation result of the training dataset;
and if the first prediction result meets a fourth preset threshold, inputting a plurality of parameters corresponding to the first prediction result into a fourth model for prediction to obtain a second prediction result, wherein the second prediction result represents weight distribution of the plurality of parameters.
And adjusting the first prediction result according to the second prediction result to obtain a first result.
On the other hand, the embodiment of the invention provides a machine room equipment on-shelf recommendation system, which comprises:
the first module is used for acquiring service information, resource information and dynamic ring information; the service information comprises U-bit space information of the overhead equipment, rated power of the overhead equipment, user names and density of the overhead equipment; the resource information comprises a standard load value, a U-bit space and bearing information of the machine room cabinet; the movable ring information comprises air conditioner refrigerating capacity, temperature, humidity and electricity load of a machine room;
the second module is used for inputting the service information, the resource information and the dynamic ring information into a trained prediction model to obtain a plurality of first schemes;
the third module is used for sequentially scoring the plurality of first schemes according to a preset scoring system to obtain a plurality of comprehensive influence scores;
a fourth module, configured to determine a simulation scheme set according to the plurality of comprehensive impact scores and a first preset threshold;
and a fifth module, configured to acquire an external instruction, determine an on-shelf scheme according to the external instruction and the simulation scheme set, and send the on-shelf scheme to a resource system to execute a preemption operation, so as to generate a pre-acceptance label.
On the other hand, the embodiment of the invention provides a device for recommending the equipment in the machine room on the shelf, which comprises the following components:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the method described in the method embodiments above.
In another aspect, embodiments of the present invention provide a computer readable storage medium, in which a processor executable program is stored, which when executed by a processor is configured to perform the method described in the previous method embodiments.
The embodiment of the invention has the following beneficial effects: according to the embodiment, service information is determined according to acquired service requirements, the resource information and the dynamic ring information are acquired through communication with a resource system and dynamic ring equipment respectively, the service information and the resource information are matched to obtain first data information, then the first data information and the dynamic ring information are input into a trained prediction model to obtain a plurality of first schemes, the plurality of first schemes are scored according to a preset scoring system to obtain a plurality of comprehensive influence scores corresponding to the plurality of first schemes, a plurality of simulation schemes are determined according to the plurality of comprehensive influence scores and a first preset threshold value, a simulation scheme set is obtained according to the plurality of simulation schemes, then an external input instruction is received, an on-shelf scheme is determined from the simulation scheme set according to the external input instruction, and the on-shelf scheme is sent to the resource system to perform a preemption operation, so that a pre-acceptance label is generated; the scheme planning is carried out by combining the movable ring information of the machine room cabinet, so that the applicability, rationality and scheme execution stability of the scheme planning are improved; by scoring the scheme, the resource allocation is optimized, and the resource utilization rate is improved.
Drawings
Fig. 1 is a schematic step flow diagram of a method for recommending on-shelf equipment in a machine room according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a step of obtaining a comprehensive influence score in a machine room equipment on-shelf recommendation method according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of a step of performing data synchronization update in a machine room equipment on-shelf recommendation method according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of steps for performing digital twin simulation in a method for recommending equipment on a machine room according to an embodiment of the present invention;
fig. 5 is a schematic flowchart of a training step of a prediction model in a machine room equipment on-shelf recommendation method according to an embodiment of the present invention;
fig. 6 is a schematic flowchart of a training step of a training data set in a machine room equipment on-shelf recommendation method according to an embodiment of the present invention;
fig. 7 is a schematic diagram of digital twin simulation visualization in a machine room equipment on-shelf recommendation method provided by an embodiment of the invention;
FIG. 8 is a schematic flow chart of steps of a specific embodiment provided in an embodiment of the present invention;
fig. 9 is a block diagram of a machine room equipment on-shelf recommendation system according to an embodiment of the present invention;
fig. 10 is a block diagram of a device for recommending on-shelf equipment in a machine room according to an embodiment of the present invention.
Detailed Description
The invention will now be described in further detail with reference to the drawings and to specific examples. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
In the following description, the terms "first", "second", "third" and the like are merely used to distinguish similar objects and do not represent a specific ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a specific order or sequence, as permitted, to enable embodiments of the invention described herein to be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the embodiments of the invention is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.
Before describing embodiments of the present invention in further detail, the terms and terminology involved in the embodiments of the present invention will be described, and the terms and terminology involved in the embodiments of the present invention will be used in the following explanation.
Simulation evaluation: the method comprises the steps of performing simulation evaluation on existing space resources, energy consumption resources, service resources and cold energy resources of a machine room to obtain evaluation scores;
digital twinning: the simulation process of multiple disciplines, multiple physical quantities, multiple scales and multiple probabilities is integrated by utilizing data such as a physical model, sensor update and operation history, mapping is completed in a virtual space, so that the full life cycle process of corresponding entity equipment is reflected, and 1:1 simulation modeling of resource data is presented in a machine room resource management platform;
ARIMA model: the autoregressive integral moving average model (Autoregressive Integrated Moving Average Model) is a statistical model for time series analysis and prediction;
regression tree model: regression trees are a variation of decision trees for establishing nonlinear relationships between features and objects;
evaluation of prediction effect: the prediction effect evaluation is a process for measuring the performance of a prediction model, and involves comparing the prediction result of the model with an actual observation value to determine the accuracy and reliability of the model;
Root Mean Square Error (RMSE): the root mean square error is an index for measuring the error of a prediction model, calculates the average value of the squares of the differences between the predicted value and the actual observed value, and squares the average value;
mean Absolute Error (MAE): the average absolute error is another index for measuring the error of the prediction model, and calculates the average value of the absolute value of the difference between the predicted value and the actual observed value;
WebSocket push: as a communication protocol, it is one of server pushing technologies, to push resource data to a mobile terminal;
centralized deployment, the centralized deployment of equipment/service is preferentially considered, resources are centralized as much as possible according to the stored service/new service, and the final position is determined after calculation and evaluation of the U-bit space occupied by the upper equipment and rated power. The precondition of the method is to evaluate and analyze the machine room stock service and the new service, and the system can concentrate the same user and the same type of service resources as much as possible so as to meet the requirements of light splitting and jump connection among services. According to the recommended evaluation result, the system determines the final equipment deployment position so as to ensure the maximum utilization efficiency of the resources;
the distributed deployment is carried out, whether the residual space of the cabinet can meet the resources required by the upper frame equipment (the lower limit of the space resources is not limited in calculation) is preferentially considered, and then the final position is determined by calculating and evaluating the U-bit space occupied by the upper frame and the rated power. The precondition of the mode is whether the residual space of the cabinet can meet the resources required by the equipment to be erected, and when the distributed deployment is carried out, the primary consideration is whether the residual space of the cabinet is enough to accommodate the equipment which needs to be erected, and the lower limit of the space resources is not limited. The final equipment decentralized deployment location is then determined by a calculated evaluation of the rated power of the overhead equipment. This ensures that the equipment can be reasonably distributed among the different cabinets to meet resource demands and avoid overcrowding or wasting space.
As shown in fig. 1, an embodiment of the present invention provides a method for recommending on-shelf equipment in a machine room, which includes the following steps.
S100, acquiring service information, resource information and dynamic ring information; the service information comprises U-bit space information of the on-shelf equipment, rated power of the on-shelf equipment, user name, equipment weight, equipment density and density of the on-shelf equipment; the resource information comprises a standard load value, a U-bit space and bearing information of the machine room cabinet; the movable ring information comprises air conditioning refrigerating capacity, temperature, humidity and electricity load of the machine room.
Specifically, before performing on-frame simulation of equipment in a machine room to obtain a simulation scheme, basic data needs to be acquired; the basic data can be acquired through various ways, firstly, the related resource data of the machine room cabinet of the operator can be acquired from the data center of the resource system by connecting the resource system of the operator and accessing the data center of the resource system and writing a database query statement, such as a standard load value, a U-bit space, bearing information and the like of the machine room cabinet; then, acquiring the business requirements of the clients, and extracting relevant business information such as user names, cabinet models required by the businesses, cabinet power and the like from the business requirements; in practical application, after the machine room cabinet is put on shelf for service operation, the environmental state in the machine room can be influenced by machine room equipment, for example, after the machine room cabinet is put on shelf for high-power service, the electricity load of the machine room can be increased, meanwhile, the machine room cabinet can be operated at high power, the heating value is increased, and new requirements are also provided for the refrigerating capacity of an air conditioner in the machine room, so that the moving ring information of moving ring equipment in the machine room also needs to be acquired in real time, and the scheme simulation is performed by synthesizing the moving ring information.
S200, inputting the service information, the resource information and the dynamic ring information into a trained prediction model to obtain a plurality of first schemes.
Specifically, after service information, resource information and dynamic ring information are obtained through various ways, the data are input into a trained prediction model to perform scheme simulation and prediction; the prediction model is based on the resource information and the dynamic ring information, a simulation scheme is constructed according to the requirements in the service information, the simulation scheme is used for simulating the change conditions of the U-bit space, the cabinet power, the machine room environment and the like of the machine room cabinet after the service is put on shelf, and different simulation schemes are obtained by adjusting the resource proportion of the requirements in the service information.
And S300, sequentially scoring the first schemes according to a preset scoring system to obtain a plurality of comprehensive influence scores.
Specifically, after different simulation schemes are obtained, the simulation schemes are scored through a set of preset scoring system, comprehensive influence scores of all the simulation schemes are obtained, influences on the existing machine room cabinet after equipment is put on shelf according to the simulation schemes are evaluated according to the comprehensive influence scores, and therefore the optimal simulation scheme is screened out.
S400, determining a simulation scheme set according to a plurality of comprehensive influence scores and a first preset threshold.
Specifically, a plurality of simulation schemes are obtained, and after the simulation schemes are scored through a preset scoring system to obtain comprehensive influence scores, the comprehensive influence scores are sequentially compared with a first preset threshold; if the comprehensive influence score is lower than a first preset threshold value, indicating that the actual resources and the environmental conditions of the machine room cabinet do not have the condition of carrying out equipment loading according to the simulation scheme; otherwise, the existing actual resources and environmental conditions of the machine room cabinet are provided with the conditions for carrying out equipment loading according to the simulation scheme, and the equipment loading can be implemented according to the simulation scheme.
S500, acquiring an external instruction, determining an on-shelf scheme according to the external instruction and the simulation scheme set, and sending the on-shelf scheme to a resource system to execute a preemption operation so as to generate a pre-acceptance label.
Specifically, in a specific embodiment, the obtained multiple simulation schemes are provided for the user object to select, the simulation scheme selected by the user object is used as an on-shelf scheme, the on-shelf scheme is sent to a resource system of the machine room, and the resource system performs preemption operation on cabinet resources in the machine room according to the on-shelf scheme, so that preparation is made for the on-shelf of subsequent equipment, and meanwhile, a pre-acceptance label is generated, so that the business handling flow is shortened.
Optionally, scoring the first scheme according to a preset scoring system to obtain a comprehensive influence score, where a specific step flow is shown in fig. 2:
s210, determining a first data set and a weight corresponding to the first data set according to a first scheme; the first data set comprises U-bit space data of the equipment cabinet after equipment is put on shelf, environment temperature data of the equipment cabinet after equipment is put on shelf and power load data of the equipment cabinet after equipment is put on shelf.
Specifically, in a specific embodiment, after service data, resource data and dynamic ring data are input into a prediction model, a plurality of first schemes are obtained, data related to machine room resources and machine room environments are obtained from the first schemes and are used as a first data set for scoring, for example, data such as a U-bit space of an equipment rack in the scheme, power of equipment, power consumption and the like; the ratio or weight of each resource in the scheme is determined from the first scheme, for example, the space U bit is-40%, the energy consumption environment is-30%, the network port is-20% and other factors are-10%.
S220, sequentially reading second data from the first data set, and matching the second data with a preset scoring system to obtain an influence score of the second data; the second data represents any one of U-bit space data of the equipment cabinet after the equipment is put on shelf, environment temperature data of the equipment cabinet after the equipment is put on shelf and power load data of the equipment cabinet after the equipment is put on shelf.
Specifically, in a specific embodiment, sequentially reading data from a first data set, then acquiring corresponding scoring criteria from a preset scoring system, scoring the data according to the scoring criteria, and exemplarily acquiring U-bit space data from the first data set, wherein in the scheme, the required U-bit space of the equipment is 50%, and the scoring criteria acquired from the preset scoring system are equipment with more than 80% of the U-bit space after being put on shelf, and scoring for 2 minutes; equipment with a U-bit space between 60 and 80 percent is scored for 4 points; equipment with a U-bit space between 40 and 60 percent is scored for 6 points; equipment with a U-bit space below 40% scores 10 points; and matching the data of the U-bit space required by the equipment in the scheme with the obtained scoring standard to obtain corresponding scores.
And S230, carrying out weighted summation on the influence scores of the second data according to preset weights to obtain comprehensive influence scores.
Specifically, in a specific embodiment, the U-bit space required by the device in the scheme is matched with the scoring standard one by one, so that the U-bit space required by the device in the scheme can be obtained to meet the standard of '40-60% of the U-bit space', and therefore, the score of the data of the U-bit space of the device in the scheme is 6 points; then repeating steps S220-S230 until all data in the first dataset are scored; after scoring the data in the scheme, obtaining the comprehensive influence score of the scheme through preset weight calculation; in a specific embodiment, the preset weights are respectively a space U bit-50%, a power condition-30%, and an ambient temperature-20%, the scores of the corresponding data are respectively a space U bit-6 score, a power condition-4 score, and an ambient temperature-5 score, and the comprehensive influence score of the scheme is calculated to be 6×50% +4×30% +5×20% =5.2.
Optionally, determining the simulation scheme set according to the plurality of comprehensive impact scores and the first preset threshold value, further includes the following steps:
s240, sequentially comparing the comprehensive influence scores with a first preset threshold, and taking a first scheme corresponding to the comprehensive influence score as a simulation scheme if the comprehensive influence score is greater than or equal to the first preset threshold.
Specifically, in a specific embodiment, the comprehensive impact scores of several schemes are obtained by a preset scoring system as follows: scheme one is 6.8, scheme two is 5.2, scheme three is 4.6, scheme four is 3.2, scheme five is 8.5, first preset threshold value is set to 5, the scheme is compared with the first preset threshold value in sequence, scheme one, scheme two and scheme five are used as simulation schemes, prompt information is sent to inform operators that the scores of scheme three and scheme four are lower than the set first preset threshold value, the actual resources of the machine room cannot meet the implementation of scheme three and scheme four, and operators are required to evaluate manually or reconstruct the existing resources of the machine room.
S250, determining a simulation scheme set according to a plurality of simulation schemes.
Specifically, in a specific embodiment, the first scheme, the second scheme, and the fifth scheme are obtained from the prediction model through step S240, and the first scheme, the second scheme, and the fifth scheme are used as a set of schemes, and may be sent to the front end to perform operations such as scheme selection.
Optionally, the method further includes a step flow as shown in fig. 3:
s600, acquiring a preset synchronization period, and carrying out real-time synchronization on the service information, the resource information and the dynamic ring information according to the preset synchronization period.
Specifically, in a specific embodiment, in order to improve the efficiency of scheme simulation and manage the machine room, data of different cabinets in the machine room, even data of different machine rooms, needs to be synchronized in real time, a synchronization period can be set, the system acquires the current time of the system in real time, and when the current time of the system is in the synchronization period, a synchronous task is put into a message queue or an event driving system by adopting an asynchronous synchronization mode, and real-time synchronization of the data is realized by adopting an asynchronous processing mode; and the data synchronization can be performed in a multithreading parallel mode, so that the synchronization efficiency and speed are improved.
And S700, sending the synchronized service information, the resource information and the dynamic ring information to a resource database for storage, and sending the synchronized service information, the synchronized resource information and the dynamic ring information to a mobile terminal for updating front-end data.
Specifically, in a specific embodiment, the synchronized data is sent to a database for storage, and the machine room can be monitored and analyzed according to the data in the database, for example, equipment with shorter service life in the machine room is analyzed from historical data in the database, so that replacement maintenance and the like are performed; the data storage modes comprise a relational database, a non-relational database, a distributed file system and the like, and the storage modes have the characteristics and the applicability, are selected and configured according to specific requirements, and are not particularly limited; meanwhile, the synchronized data are transmitted to the front-end equipment, so that the real-time property of the front-end information and the rear-end information is ensured, and an operator at the front end can adjust the project or the service according to the real-time synchronized data; by way of example, the synchronized data is updated and pushed to the mobile terminal device through the WebSocket pushing technology, and an operator of the mobile terminal device can know the current state of the machine room according to the synchronized data without going to the machine room or a machine room dispatching center.
Optionally, the method further includes a step flow as shown in fig. 4:
s510, determining a third data set according to the on-shelf scheme, and sending the third data set to the digital twin platform for virtual preloading to generate a virtual 3D visual model of the on-shelf scheme; the third data set comprises overhead equipment U-bit space information, overhead equipment power information, overhead equipment density information, machine room cabinet bearing information and machine room cabinet environment information.
Specifically, after the racking scheme is determined from a plurality of simulation schemes according to an external instruction, the racking scheme is directly displayed and can be understood only by a certain expertise support; if the complexity of the racking scheme is high, even professionals understand the scheme to have certain difficulty; the method comprises the steps of extracting data of an on-shelf scheme, and sending the data of the on-shelf scheme to a digital twin platform, wherein the digital twin platform constructs a visual model of the on-shelf scheme according to the data of the on-shelf scheme, and the constructed visual model is shown in fig. 7; the method comprises the steps of constructing a visual model of a machine room cabinet according to U-bit space data of an on-shelf scheme, and marking U-bit space changes after equipment of the on-shelf scheme by adopting different colors or highlights; the red background is adopted to indicate the temperature rise of the machine room in the shelving scheme, the blue color is adopted to indicate the temperature reduction of the machine room in the shelving scheme, the temperature change amplitude is indicated by changing the saturation level of the color, and the like, and the shelving scheme is intuitively displayed through the constructed visual model.
Alternatively, the training process of the predictive model is as shown in fig. 5:
s810, determining a sample data set according to a plurality of test schemes, and dividing and screening the sample data set according to preset proportions to obtain a training data set and a test data set; the test data set comprises U-bit space data of the device, power data of the device and environment data of the device.
Specifically, predicting future scale of the acquired data through a trained prediction model, and predicting proportioning relation among the data, so that a scheme model is constructed according to the data, and the influence on the machine room environment after implementation is predicted according to the constructed scheme model; therefore, acquiring data of a plurality of schemes for testing as test data for training a predictive model; according to the proportioning relation among different resource data in the test scheme, the test data are subjected to inductive classification, and then the inductive classified test data are divided into a training set and a test set according to a preset proportion; for example, according to 7:3 to divide the training set and the test set.
S820, inputting the training data set into the first model to obtain a first result;
specifically, in a specific embodiment, the prediction model includes an ARIMA model and a regression tree model, where the ARIMA model is used for time series analysis and prediction of future scale, the regression tree model is used for considering a proportioning relationship between different resources, training data is input into the ARIMA model to obtain a prediction scale, then resource data in the prediction scale is input into the regression tree model to obtain a proportioning relationship of the data, and a simulation scheme of the training data is obtained according to the prediction scale and the proportioning relationship, as a first result.
And S830, calculating the prediction accuracy according to the first result, and carrying out parameter adjustment on the first model according to the prediction accuracy and a second preset threshold value until the prediction accuracy meets the second preset threshold value to obtain a second model.
Specifically, in this embodiment, the training set divided in step S810 is input into the ARIMA model and the regression tree model for training, and parameters of the ARIMA model and the regression tree model are adjusted according to the output result of the model until the output result of the model meets the preset requirement, and training of the ARIMA model and the regression tree model is terminated, and test evaluation of the model is entered.
S840, inputting the test data set into a second model to obtain a second result; calculating a performance value according to the test data set and the second result, and taking the second model as a prediction model if the performance value reaches a third preset threshold value; wherein the performance value comprises a root mean square error and an average absolute error.
Specifically, after the model is trained in step S820, the trained model is evaluated through a test data set, and accuracy and effect of the model in future scale prediction are evaluated, and in this embodiment, prediction performance of the model is measured through Root Mean Square Error (RMSE) and Mean Absolute Error (MAE); the smaller the root mean square error value is, the better the fitting effect of the trained model is, and the closer the output result obtained by inputting the test data set into the model is to the actual observation value, namely the test data set; the smaller the average absolute error, the smaller the average predicted deviation of the model from the input data, and the closer the output result of the model to the actual observed value, i.e. the test data set.
Optionally, the first model includes a third model and a fourth model, and the training data set is input into the first model to obtain a first result, and a specific step flow is shown in fig. 6:
s821, inputting the training data set into a third model for prediction to obtain a first prediction result; the first prediction result represents an on-shelf simulation result of the training data set.
Specifically, the first model is an ARIMA model, which can process the sequence data, predict the trend, split the sequence data into trend, stage and random components, and then model by a combination of differential and autoregressive moving averages, and the obtained prediction formula is:
Y t ＝c+φ 1 Y t-1 +θ 1 ε t-1 +…+φ p Y t-p +θ q ε t-q +ε t
wherein Y is t Time series data of time t, c is a constant term, Y t-1 Time series data of time t-1, Y t-p Epsilon as time series data of time t-p t-1 Number of errors for time t-1According to ε t-q Epsilon as error data of time t-q t Error data for time t, phi 1 Is the relation parameter of time series data of time t and time series data of time t-1, phi p Is a relation parameter of time series data of time t and time series data of time t-p, theta 1 Is a relation parameter of time series data of time t and error data of time t-1, theta q Is a relation parameter of time series data of time t and error data of time t-q.
S822, if the first prediction result meets a fourth preset threshold, inputting a plurality of parameters corresponding to the first prediction result into a fourth model for prediction to obtain a second prediction result, wherein the second prediction result represents weight distribution of the plurality of parameters.
Specifically, after a training data set is input into an ARIMA model to obtain a predicted future scale, various resource data are extracted from an output result of the ARIMA model, then the resource data are input into a regression tree model serving as a second model, a predicted value of each child node in the regression tree model is calculated, and influence factors in the resource data are predicted, so that weight distribution and relation of different resources are obtained.
S823, adjusting the first prediction result according to the second prediction result to obtain a first result.
Specifically, in this embodiment, future scale data output by the first model is adjusted according to the obtained weight distribution and relationship of different resources, so as to obtain a predicted simulation scheme.
In a specific embodiment, as shown in fig. 8, resource information and service information of a machine room are obtained through an http interface, wherein the resource information of the machine room comprises a standard load value, a U-bit space, load bearing information and the like of a cabinet; the service information comprises service details such as user name, bandwidth, type, IP address and the like; information of movable ring equipment in the machine room is obtained through an interconnection C interface, wherein the information comprises air conditioning refrigerating capacity, temperature and humidity of the machine room, switching power supply state, rated power, electricity load and the like of the machine room; then, the acquired service information, resource information and dynamic ring information are subjected to data synchronization and sent to a resource database for storage, and meanwhile, the states of the service information, the resource information and the dynamic ring information are monitored in real time; then, the system inquires and acquires corresponding resource data from a database according to equipment information of service requirements, and acquires corresponding data information according to requirements of virtual simulation evaluation, for example, information such as overhead equipment space information, overhead equipment rated power, service customer names, equipment weight, equipment density, overhead equipment density and the like is needed for virtual simulation evaluation so as to ensure normal operation of the virtual simulation evaluation, for example, the overhead equipment space information measures whether available space of a machine room meets the requirements of overhead equipment; besides the necessary data information, the data information such as the requirements of the high-power cabinet and the required quantity of the service connection fiber cores can be acquired, so that the accuracy of recommended deployment and the accuracy of service matching are improved; after the above data information is acquired, the system starts virtual simulation and evaluates by an algorithm, such as: judging whether the customer is an existing customer or not based on the customer name, if the customer is the existing customer, calculating and recommending the current acceptance service to be connected with the main and standby service according to the user demand; if a new customer does not consider a non-empty cabinet, the system only recommends an empty cabinet; based on the number of the on-shelf devices and whether space resources of the machine room are met (a local station and the machine room can be appointed) or not, performing next power calculation after the space resources are met; if the machine room is not satisfied, automatically replacing the machine room or initiating a machine room reconstruction demand reminding; the rated power of the overhead and the standard power of the machine room cabinet are evaluated similar to the U-bit space in front, and the deployment requirement is met if the power and the power supply system meet the conditions. If the standard load of the idle cabinet in the machine room is not satisfied or the redundancy of the power supply system is insufficient, the machine room is automatically replaced or the machine room reconstruction demand reminding is initiated; after all the resource data are evaluated, determining a resource deployment mode selected by a service client; the resource deployment mode comprises centralized deployment and decentralized deployment, wherein the centralized deployment takes priority on resources of the whole cabinet and the U-bit space of the cabinet, the decentralized deployment takes priority on whether the residual U-bit space of the cabinet can meet the space occupied by the overhead equipment or not, the space resources are utilized to the maximum, and the lower limit of the space resources is not limited during calculation; the different deployment modes are different in proportion and distribution of resources, scheme simulation is carried out according to the selected resource deployment mode to obtain a simulation scheme, then the obtained simulation scheme is pushed to a resource system of a machine room, the system performs preemption according to the simulation scheme, a corresponding pre-acceptance label is generated, front-end personnel decides whether to accept formally according to service conditions, and if so, a corresponding cabinet resource is selected according to the pre-acceptance label to issue a service acceptance list, so that a service formally acceptance flow is completed.
The embodiment of the invention has the following beneficial effects: according to the embodiment, service information is determined according to acquired service requirements, the resource information and the dynamic ring information are acquired through communication with a resource system and dynamic ring equipment respectively, the service information and the resource information are matched to obtain first data information, then the first data information and the dynamic ring information are input into a trained prediction model to obtain a plurality of first schemes, the plurality of first schemes are scored according to a preset scoring system to obtain a plurality of comprehensive influence scores corresponding to the plurality of first schemes, a plurality of simulation schemes are determined according to the plurality of comprehensive influence scores and a first preset threshold value, a simulation scheme set is obtained according to the plurality of simulation schemes, then an external input instruction is received, an on-shelf scheme is determined from the simulation scheme set according to the external input instruction, and the on-shelf scheme is sent to the resource system to perform a preemption operation, so that a pre-acceptance label is generated; after acquiring service information, resource information and dynamic ring information, carrying out real-time synchronization on the service information, the resource information and the dynamic ring information according to the acquired timing tasks, sending the synchronized service information, resource information and dynamic ring information to a database for storage, and sending the synchronized service information, resource information and dynamic ring information to mobile terminal updating front-end data; after the on-shelf scheme is determined, transmitting the data of the on-shelf scheme to a digital twin platform, and generating a virtual 3D visual model of the on-shelf scheme for display by the digital twin platform according to the data of the on-shelf scheme; the scheme planning is carried out by combining the movable ring information of the machine room cabinet, so that the applicability, rationality and scheme execution stability of the scheme planning are improved; by scoring the scheme, the resource allocation is optimized, and the resource utilization rate is improved; the acquired data information is sent to the front end for data updating after real-time synchronization, so that real-time data communication of the front end and the rear end is realized; and 3D visualization is performed on the on-shelf scheme through the digital twin platform, so that user experience is improved.
As shown in fig. 9, the embodiment of the present invention further provides a system for recommending on-shelf equipment in a machine room, including:
the first module is used for acquiring service information, resource information and dynamic ring information; the service information comprises U-bit space information of the on-shelf equipment, rated power of the on-shelf equipment, user names and density of the on-shelf equipment; the resource information comprises a standard load value, a U-bit space and bearing information of the machine room cabinet; the movable ring information comprises air conditioner refrigerating capacity, temperature, humidity and electricity load of the machine room;
the second module is used for inputting the service information, the resource information and the dynamic ring information into the trained prediction model to obtain a plurality of first schemes;
the third module is used for sequentially scoring the first schemes according to a preset scoring system to obtain a plurality of comprehensive influence scores;
a fourth module, configured to determine a simulation scheme set according to a plurality of comprehensive impact scores and a first preset threshold;
and the fifth module is used for acquiring the external instruction, determining an on-shelf scheme according to the external instruction and the simulation scheme set, and sending the on-shelf scheme to the resource system so as to execute the preemption operation and generate the pre-acceptance label.
It can be seen that the foregoing method embodiments are applicable to the system embodiment, and the functions specifically implemented by the system embodiment are the same as those of the foregoing method embodiment, and the beneficial effects achieved by the foregoing method embodiment are the same as those achieved by the foregoing method embodiment.
As shown in fig. 10, the embodiment of the present invention further provides a device for recommending on-shelf equipment in a machine room, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor implements the machine room equipment on-shelf recommendation method steps of the foregoing method embodiment.
Wherein the memory is operable as a non-transitory computer readable storage medium storing a non-transitory software program and a non-transitory computer executable program. The memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes remote memory provided remotely from the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
It can be seen that the foregoing method embodiments are applicable to the present apparatus embodiment, and the functions specifically implemented by the present apparatus embodiment are the same as those of the foregoing method embodiment, and the beneficial effects achieved by the foregoing method embodiment are also the same.
Furthermore, embodiments of the present application disclose a computer program product or a computer program, which is stored in a computer readable storage medium. The computer program may be read from a computer readable storage medium by a processor of a computer device, the processor executing the computer program causing the computer device to perform the method as described above. Similarly, the content in the above method embodiment is applicable to the present storage medium embodiment, and the specific functions of the present storage medium embodiment are the same as those of the above method embodiment, and the achieved beneficial effects are the same as those of the above method embodiment.
The embodiment of the present invention also provides a computer-readable storage medium storing a processor-executable program for implementing the foregoing method when executed by a processor.
It is to be understood that all or some of the steps, systems, and methods disclosed above may be implemented in software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
While the preferred embodiment of the present invention has been described in detail, the invention is not limited to the embodiment, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the invention, and these modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (10)
1. The machine room equipment on-shelf recommendation method is characterized by comprising the following steps of:
acquiring service information, resource information and dynamic ring information; the service information comprises U-bit space information of the on-shelf equipment, rated power of the on-shelf equipment, user names and density of the on-shelf equipment; the resource information comprises a standard load value, a U-bit space and bearing information of the machine room cabinet; the movable ring information comprises air conditioner refrigerating capacity, temperature, humidity and electricity load of a machine room;
inputting the service information, the resource information and the dynamic ring information into a trained prediction model to obtain a plurality of first schemes;
sequentially scoring the first schemes according to a preset scoring system to obtain a plurality of comprehensive influence scores;
determining a simulation scheme set according to the comprehensive influence scores and a first preset threshold;
And acquiring an external instruction, determining an on-shelf scheme according to the external instruction and the simulation scheme set, and sending the on-shelf scheme to a resource system to execute a preemption operation so as to generate a pre-acceptance label.
2. The method according to claim 1, wherein scoring the first pattern according to a preset scoring system results in a composite impact score, specifically comprising:
determining a first data set and a weight corresponding to the first data set according to a first scheme; the first data set comprises U-bit space data of the equipment cabinet after equipment is put on shelf, environment temperature data of the equipment cabinet after equipment is put on shelf and power load data of the equipment cabinet after equipment is put on shelf;
sequentially reading second data from the first data set, and matching the second data with the preset scoring system to obtain an influence score of the second data; the second data represents any one of U-bit space data of the equipment rack after the equipment is put on shelf, environment temperature data of the equipment rack after the equipment is put on shelf and power load data of the equipment rack after the equipment is put on shelf;
and carrying out weighted summation on the influence scores of the second data according to the weights to obtain comprehensive influence scores.
3. The method according to claim 1, wherein said determining a set of simulation schemes based on said number of said integrated impact scores and a first preset threshold value, in particular comprises:
sequentially comparing a plurality of comprehensive influence scores with a first preset threshold value, and taking the first scheme corresponding to the comprehensive influence score as a simulation scheme if the comprehensive influence score is larger than or equal to the first preset threshold value;
a simulation scheme set is determined from a number of the simulation schemes.
4. The method according to claim 1, wherein the method further comprises:
acquiring a preset synchronization period, and synchronizing the service information, the resource information and the dynamic ring information in real time according to the preset synchronization period;
and sending the synchronized service information, the resource information and the moving ring information to a resource database for storage, and sending the synchronized service information, the synchronized resource information and the moving ring information to a mobile terminal for updating front-end data.
5. The method according to claim 1, wherein the method further comprises:
and sending the virtual preloading to a digital twin platform according to the shelving scheme, and generating a virtual 3D visual model of the shelving scheme.
6. The method according to claim 1, wherein the training process of the predictive model is as follows:
determining a sample data set according to a plurality of test schemes, and dividing and screening the sample data set according to preset proportions to obtain a training data set and a test data set; the sample data set comprises U-bit space data of the equipment, power data of the equipment and environment data of the equipment;
inputting the training data set into a first model to obtain a first result;
calculating prediction accuracy according to the first result, and performing parameter adjustment on the first model according to the prediction accuracy and a second preset threshold until the prediction accuracy meets the second preset threshold to obtain a second model;
inputting the test data set into the second model to obtain a second result; calculating a performance value according to the test data set and the second result, and taking the second model as a prediction model if the performance value reaches a third preset threshold; wherein the performance value comprises a root mean square error and an average absolute error.
7. The method according to claim 6, wherein the first model comprises a third model and a fourth model, and wherein the inputting the training dataset into the first model results in a first result, comprising:
Inputting the training data set into a third model for prediction to obtain a first prediction result; wherein the first predictive result characterizes an on-shelf simulation result of the training dataset;
if the first prediction result meets a fourth preset threshold, inputting a plurality of parameters corresponding to the first prediction result into a fourth model for prediction to obtain a second prediction result, wherein the second prediction result represents weight distribution of the plurality of parameters;
and adjusting the first prediction result according to the second prediction result to obtain a first result.
8. An equipment on-shelf recommendation system for a machine room, comprising:
the first module is used for acquiring service information, resource information and dynamic ring information; the service information comprises U-bit space information of the on-shelf equipment, rated power of the on-shelf equipment, user names and density of the on-shelf equipment; the resource information comprises a standard load value, a U-bit space and bearing information of the machine room cabinet; the movable ring information comprises air conditioner refrigerating capacity, temperature, humidity and electricity load of a machine room;
the second module is used for inputting the service information, the resource information and the dynamic ring information into a trained prediction model to obtain a plurality of first schemes;
The third module is used for sequentially scoring the plurality of first schemes according to a preset scoring system to obtain a plurality of comprehensive influence scores;
a fourth module, configured to determine a simulation scheme set according to the plurality of comprehensive impact scores and a first preset threshold;
and a fifth module, configured to acquire an external instruction, determine an on-shelf scheme according to the external instruction and the simulation scheme set, and send the on-shelf scheme to a resource system to execute a preemption operation, so as to generate a pre-acceptance label.
9. Machine room equipment puts on shelf and recommends device, characterized by comprising:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the method of any of claims 1-7.
10. A computer readable storage medium, in which a processor executable program is stored, characterized in that the processor executable program is for performing the method according to any of claims 1-7 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465202.9A CN117540975A (en) | 2023-11-06 | 2023-11-06 | Machine room equipment on-shelf recommendation method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465202.9A CN117540975A (en) | 2023-11-06 | 2023-11-06 | Machine room equipment on-shelf recommendation method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117540975A true CN117540975A (en) | 2024-02-09 |
Family
ID=89783267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311465202.9A Pending CN117540975A (en) | 2023-11-06 | 2023-11-06 | Machine room equipment on-shelf recommendation method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117540975A (en) |
-
2023
- 2023-11-06 CN CN202311465202.9A patent/CN117540975A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108364085A (en) | A kind of take-away distribution time prediction technique and device | |
| US20210166181A1 (en) | Equipment management method, device, system and storage medium | |
| CN112926941B (en) | Management method and device of financial auditing rules, storage medium and server | |
| KR20210023119A (en) | System and Method for Restaurant Ingredients Inventory Management and Order Management using Neural Networks-based Artificial Intelligence | |
| CN111353794B (en) | Data processing method, supply chain scheduling method and device | |
| CN113360353B (en) | Test server and cloud platform | |
| EP3961327A1 (en) | Assembly assistance device and method | |
| Zhao et al. | Market thickness in online food delivery platforms: The impact of food processing times | |
| CN110689177B (en) | Method and device for predicting order preparation time, electronic equipment and storage medium | |
| CN115860548B (en) | SaaS one-stop platform management method, system and medium based on big data | |
| CN117540975A (en) | Machine room equipment on-shelf recommendation method, system, device and storage medium | |
| CN114757448B (en) | Manufacturing inter-link optimal value chain construction method based on data space model | |
| CN115062676B (en) | Data processing method, device and computer readable storage medium | |
| CN115032957B (en) | Production scheduling method and device, storage medium and electronic equipment | |
| CN114727309A (en) | Network optimization method and equipment | |
| CN115796925B (en) | Sales data statistics method and system based on cloud platform | |
| CN111598188A (en) | Method and device for identifying position of target store, storage medium and electronic equipment | |
| CN117273318B (en) | Material alignment sleeve analysis method and device | |
| CN116362462B (en) | Full-closed-loop production management system based on Internet of things and big data analysis | |
| CN117499817B (en) | Distributed ammeter acquisition system and acquisition method | |
| CN117667585B (en) | Operation and maintenance efficiency evaluation method and system based on operation and maintenance quality management database | |
| CN117933857B (en) | Logistics order scheduling method and equipment for after-sales platform and readable storage medium | |
| US20230267007A1 (en) | System and method to simulate demand and optimize control parameters for a technology platform | |
| CN117829901A (en) | Control method and device of accessory management system and readable storage medium | |
| CN115204518A (en) | Supply chain information processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |