CN117863199A - Robot based on task scheduling, inspection method and related device - Google Patents
Robot based on task scheduling, inspection method and related device Download PDFInfo
- Publication number
- CN117863199A CN117863199A CN202410124897.2A CN202410124897A CN117863199A CN 117863199 A CN117863199 A CN 117863199A CN 202410124897 A CN202410124897 A CN 202410124897A CN 117863199 A CN117863199 A CN 117863199A
- Authority
- CN
- China
- Prior art keywords
- cabinet
- task
- load
- robot
- task quantity
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005265 energy consumption Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 abstract description 16
- 230000000694 effects Effects 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 239000000306 component Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Abstract
The application provides a robot based on task scheduling, a routing inspection method and a related device, wherein a loadable task quantity input set is input into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of a cabinet, the cabinet is divided into a high-load cabinet and a low-load cabinet according to the loadable task quantity prediction result of the cabinet, and finally, the task quantity is distributed to the high-load cabinet and the low-load cabinet according to the work quantity to be scheduled of a machine room, and the robot is enabled to perform routing inspection according to the task quantity distributed by the cabinet. According to the method and the device, the robot can carry out inspection according to the actual load condition and processing capacity of the cabinet, resource waste and load unbalance are avoided, meanwhile, the moving distance and time of the robot are reduced, and the inspection efficiency of the robot is improved. In addition, the robot can be dynamically adjusted and optimized under different working loads, so that the optimal inspection effect is achieved.
Description
Technical Field
The application belongs to the technical field of robot control, and particularly relates to a robot based on task scheduling, a patrol method and a related device.
Background
In order to improve the efficiency and quality of data center operation and maintenance, intelligent inspection schemes based on robot technology have appeared in recent years. The intelligent inspection robot is intelligent equipment capable of autonomous navigation, equipment state identification, environment data acquisition and operation and maintenance task execution. The intelligent inspection robot can automatically complete the inspection task according to a preset plan and a route.
However, the existing intelligent inspection robot has some defects, and the main appearance is that: the inspection strategy of the intelligent inspection robot is relatively fixed, and the capability of dynamic adjustment according to the task scheduling condition of the data center is lacking; the inspection efficiency of the intelligent inspection robot is limited by the loadable task amount of the cabinet, and the processing capacity of the high-load cabinet cannot be fully utilized; the inspection result of the intelligent inspection robot lacks mutual feedback with the task scheduling system, so that reasonable utilization of resources and load balancing cannot be realized.
Disclosure of Invention
Aiming at the technical problems that an intelligent inspection robot in a data center is fixed in inspection strategy, low in inspection efficiency and lack in inspection result and a task scheduling system are fed back mutually, the application provides a robot based on task scheduling, an inspection method and related devices.
In order to achieve the above purpose, the present application is implemented by adopting the following technical scheme:
in a first aspect, the present application proposes a robot inspection method based on task scheduling, including:
acquiring a loadable task quantity input set of a cabinet;
inputting the loadable task quantity input set into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of the cabinet;
dividing the cabinet into a high-load cabinet and a low-load cabinet according to the forecasting result of the loadable task quantity of the cabinet; the forecast result of the bearable task quantity of the high-load cabinet is higher than a preset bearable task quantity threshold value, and the forecast result of the bearable task quantity of the low-load cabinet is lower than the preset bearable task quantity threshold value;
and distributing task amounts to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amounts distributed by the cabinets.
Preferably, the loadable task quantity input set includes: the location of the cabinet in the data room, the CPU utilization of the data center, the equipment system energy consumption of the cabinet, the historical fault data and the running temperature.
Preferably, the method for determining the preset sustainable task quantity threshold includes:
wherein Y is 1 To preset the threshold value of the bearable task quantity, K 1 The weight value of the cabinet position is W which is determined according to the position of the cabinet in the data machine room, K 2 The machine cabinet performance weight is determined by S, which is the weight determined according to the data quantity processed by the machine cabinet in unit time, and L, which is the weight determined according to the importance degree of the data type processed by the machine cabinet.
Preferably, the distributing task amount to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amount distributed by the cabinet, includes:
if the machine room to-be-scheduled workload is greater than the preset scheduling amount upper threshold, the machine room to-be-scheduled workload is distributed to a high-load cabinet, and if the residual machine room to-be-scheduled workload exists, the residual machine room to-be-scheduled workload is distributed to a low-load cabinet around the high-load cabinet; the robot sequentially carries out inspection according to the forecast result of the loadable task quantity of the high-load cabinet from large to small and the work quantity to be scheduled distributed by the low-load cabinet from large to small;
if the work load to be scheduled of the machine room is smaller than the lower threshold value of the preset scheduling amount, the work load to be scheduled of the machine room is distributed to the high-load cabinet; the robots sequentially carry out inspection according to the work load to be scheduled distributed by the high-load cabinet from large to small;
if the work load to be scheduled of the machine room is between the upper threshold value of the preset scheduling amount and the lower threshold value of the preset scheduling amount, the work load to be scheduled of the machine room is evenly distributed between a high-load cabinet and a low-load cabinet; and the robot sequentially patrols and examines each cabinet according to the global patrol route.
Preferably, the method for determining the CPU utilization of the data center includes:
wherein s is t For data center CPU utilization during time period t,total number of servers in the data center, F is the capacity of each server, mu t Is the IT demand during time period t.
Preferably, the method for determining the energy consumption of the cabinet equipment system includes:
P IT,t ＝m t p idle +(p peak -p idle )μ t /F
wherein P is IT,t For the energy consumption of the cabinet equipment system in the time period t, m t For the number of active servers in the data center during time period t, p peak P is the peak power consumption of the server idle Is the energy consumption of the server when idle.
Preferably, the loadable task quantity input set includes: the position of the cabinet in the data machine room, the CPU utilization rate of the data center, the energy consumption of equipment systems of the cabinet, the running temperature and the real-time state data of the cabinet.
In a second aspect, the present application proposes a robot inspection system based on task scheduling, including:
the data acquisition module is used for acquiring a loadable task quantity input set of the cabinet;
the prediction module is used for inputting the loadable task quantity input set into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of the cabinet;
the classification module is used for dividing the cabinet into a high-load cabinet and a low-load cabinet according to the forecasting result of the loadable task quantity of the cabinet; the forecast result of the bearable task quantity of the high-load cabinet is higher than a preset bearable task quantity threshold value, and the forecast result of the bearable task quantity of the low-load cabinet is lower than the preset bearable task quantity threshold value;
and the distribution module is used for distributing task amounts to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amounts distributed by the cabinets.
Preferably, the data acquisition module includes:
the position acquisition module is used for acquiring the position of the cabinet in the data machine room;
the utilization rate acquisition module is used for acquiring the CPU utilization rate of the data center;
the energy consumption acquisition module is used for acquiring the energy consumption of the equipment system of the cabinet;
the fault acquisition module is used for acquiring historical fault data;
and the temperature acquisition module is used for acquiring the running temperature.
Preferably, the data acquisition module includes:
the position acquisition module is used for acquiring the position of the cabinet in the data machine room;
the utilization rate acquisition module is used for acquiring the CPU utilization rate of the data center;
the energy consumption acquisition module is used for acquiring the energy consumption of the equipment system of the cabinet;
the sensor module is used for acquiring historical fault data;
and the temperature acquisition module is used for acquiring real-time state data of the cabinet.
In a third aspect, the present application proposes a robot based on task scheduling, comprising a robot body and a control unit for controlling the movement of the robot body; the control unit stores a computer program which, when executed by a processor, realizes the steps of the robot inspection method based on task scheduling.
In a fourth aspect, the present application proposes an electronic device comprising:
a memory for storing a computer program;
and the processor is used for realizing the robot inspection method based on task scheduling when executing the computer program.
In a fifth aspect, the present application proposes a computer readable storage medium, in which a computer program is stored, which when executed by a processor, implements the steps of the above-mentioned robot inspection method based on task scheduling.
Compared with the prior art, the application has the following beneficial effects:
the application provides a robot inspection method based on task scheduling, which is characterized in that a loadable task quantity input set is input into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of a cabinet, the cabinet is divided into a high-load cabinet and a low-load cabinet according to the loadable task quantity prediction result of the cabinet, finally, the task quantity is distributed to the high-load cabinet and the low-load cabinet according to the work quantity to be scheduled of a machine room, and the robot is enabled to inspect according to the task quantity distributed by the cabinet. The intelligent algorithm based on the load-bearing task quantity input set utilizes the intelligent algorithm of the load-bearing task quantity prediction model to predict the load-bearing task quantity of the cabinet, so that reasonable allocation and scheduling of machine room tasks are realized, the robot can carry out inspection according to the actual load condition and processing capacity of the cabinet, resource waste and load imbalance are avoided, meanwhile, the moving distance and time of the robot are reduced, and the inspection efficiency of the robot is improved. In addition, according to the amount of the work load to be scheduled of the machine room, different task allocation strategies and inspection strategies are adopted to adapt to different scene requirements, and the robot can be dynamically adjusted and optimized under different workloads so as to achieve the optimal inspection effect.
The application also provides a robot inspection system based on task scheduling, a robot based on task scheduling, electronic equipment and a computer readable storage medium, and all the advantages of the robot inspection method based on task scheduling are achieved.
Drawings
For a clearer description of the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and should therefore not be considered limiting in scope, and that other related drawings can be obtained according to these drawings without the inventive effort of a person skilled in the art.
Fig. 1 is a schematic flow chart of a robot inspection method based on task scheduling;
FIG. 2 is a second flow diagram of a robot inspection method based on task scheduling according to the present application;
FIG. 3 is a schematic diagram of a robotic inspection system based on task scheduling in accordance with the present application;
FIG. 4 is a schematic diagram of an electronic device of the present application;
fig. 5 is another schematic diagram of the electronic device of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the embodiments of the present application, it should be noted that, if the terms "upper," "lower," "horizontal," "inner," and the like indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, or the azimuth or the positional relationship in which the inventive product is conventionally put in use, it is merely for convenience of describing the present application and simplifying the description, and does not indicate or imply that the apparatus or element to be referred to must have a specific azimuth, be configured and operated in a specific azimuth, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.
Furthermore, the term "horizontal" if present does not mean that the component is required to be absolutely horizontal, but may be slightly inclined. As "horizontal" merely means that its direction is more horizontal than "vertical", and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
In the description of the embodiments of the present application, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," "connected," and "connected" should be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art as the case may be.
Data centers are used to store, process, and manage large amounts of data, and typically include servers, storage devices, network devices, and the like. Data centers may provide various data services such as data storage, backup and restore, data encryption and security, and the like. Data centers often require efficient power and cooling systems, highly reliable network and security systems, and intelligent monitoring and management systems. With the continued development of the digital age, the demand for data centers is also increasing. In a machine room of a data center, a cabinet is used for storing key information technology equipment such as servers, network equipment, storage equipment and the like. Wherein the server is one of the core devices of the data center. Servers are critical devices for storing and processing data that can provide efficient, secure, and reliable data storage and processing services for a variety of applications. The performance and reliability of the server directly affects the performance and reliability of the data center. The CPU is also a core component in the server and is responsible for executing instructions and processing data, and the performance of the CPU directly influences the processing capacity and efficiency of the server.
In addition, the inspection robot is generally arranged in the machine room and is mainly used for realizing inspection of the machine room, equipment detection, environment monitoring and the like. The inspection robot can improve inspection efficiency and reliability, lighten the workload of personnel and provide data support for management personnel.
At present, the inspection robot generally works according to an inspection strategy of fixed point, timing and fixed path. The robot carries out inspection of fixed point positions on equipment in a machine room according to preset time and route, such as detection of parameters of temperature, humidity, indicator lights and the like. The inspection strategy has the advantages that the equipment state in the machine room can be timely and comprehensively monitored, and faults or potential safety hazards caused by human negligence or omission are avoided. However, this strategy lacks flexibility and adaptability and cannot be dynamically adjusted and optimized according to the actual conditions and requirements in the machine room. In addition, the strategy has high requirements on navigation and positioning capabilities of the robot, so that the robot can accurately reach a specified inspection point. Therefore, a machine room inspection strategy based on a visual identification technology is also extended. The robot uses visual recognition technology to intelligently recognize and analyze the equipment in the machine room, such as the recognition of information of pointers, numbers, positions, colors and the like. The strategy has the advantages that the inspection efficiency and accuracy of the robot can be improved, the possibility of manual intervention and misjudgment can be reduced, meanwhile, the inspection range and content of the robot can be expanded, and information which is difficult to measure by a sensor or difficult to describe by language can be effectively captured and processed. However, this strategy places high demands on the vision processing capabilities of the robot to ensure that the robot is able to perform stable and reliable image recognition in complex and varying environments. This requires robots with powerful computing and storage capabilities and excellent image processing algorithms and models. In addition, some information is not available through visual information such as sound, temperature, humidity, smell, etc. This requires that the robot be equipped with other types of sensors at the same time, or cooperate with other types of inspection robots, to achieve a comprehensive monitoring of the status of the equipment.
For the above reasons, the present application proposes a robot, a tour inspection method and related devices based on task scheduling, and the following further details are described in the present application with reference to the embodiments and the accompanying drawings:
referring to fig. 1, a first flow chart of a robot inspection method based on task scheduling according to the present application may include the following steps:
s101, acquiring a loadable task quantity input set of the cabinet.
In practical application, the data content specifically included in the loadable task quantity input set of the cabinet can be adjusted according to policy requirements, prediction requirements and the like.
S102, inputting the loadable task quantity input set into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of the cabinet.
It should be noted that, the loadable task amount prediction model can predict the loadable task amount of the cabinet according to the related data that may affect the loadable task amount of the cabinet in the machine room. In practical application, the loadable task amount prediction model can be a prediction model based on artificial intelligence and machine learning technology, for example, a linear regression method, a decision tree, a random forest, a neural network and the like can be adopted. Similar models are disclosed, for example, a method for predicting network flow of a multi-task data center based on deep learning is proposed in China patent application publication No. CN116192764A, and feature information of network flow of the data center is extracted by constructing a deep learning multi-task model, so that prediction of future flow load is realized, and further task load bearing capacity of the data center can be deduced.
In practical application, the loadable task quantity prediction model needs to be trained by using a training set, and can be continuously corrected and optimized according to a prediction result in the use process, and the training of the model is a conventional technical method in the field, and is not repeated here.
The loadable task amount of a cabinet refers to the number of devices that the cabinet can accommodate and the total power of those devices. If the amount of tasks that can be carried by the cabinet is insufficient, the equipment may overheat, operate unstably or fail to work normally. The method and the device can accurately predict the loadable task quantity of the cabinet by means of the loadable task quantity prediction model.
S103, dividing the machine cabinet into a high-load machine cabinet and a low-load machine cabinet according to the prediction result of the loadable task quantity of the machine cabinet. The method comprises the steps that a loadable task quantity prediction result of a high-load cabinet is higher than a preset bearable task quantity threshold, and a loadable task quantity prediction result of a low-load cabinet is lower than the preset bearable task quantity threshold.
According to the forecasting result of the loadable task quantity of the cabinet, the cabinet is divided into a high-load cabinet and a low-load cabinet, so that different strategies can be matched conveniently according to the to-be-scheduled work quantity of the machine room. In practical application, the preset bearable task amount threshold can be set according to the practical condition of the cabinet and the requirement of the cabinet, and the application is not limited.
S104, distributing task amounts to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amounts distributed by the cabinets.
According to the method and the system, the task quantity is distributed according to the work quantity to be scheduled of the machine room and the forecasting result of the loadable task quantity of the cabinet, the inspection strategy is arranged, different scene requirements can be met, and the robot can be dynamically adjusted and optimized under different workloads, so that the optimal inspection effect is achieved.
The intelligent algorithm based on the load-bearing task quantity input set utilizes the intelligent algorithm of the load-bearing task quantity prediction model to predict the load-bearing task quantity of the cabinet, so that reasonable allocation and scheduling of machine room tasks are realized, the robot can carry out inspection according to the actual load condition and processing capacity of the cabinet, resource waste and load imbalance are avoided, meanwhile, the moving distance and time of the robot are reduced, and the inspection efficiency of the robot is improved. In addition, according to the amount of the work load to be scheduled of the machine room, different task allocation strategies and inspection strategies are adopted, so that the best inspection effect is achieved.
Referring to fig. 2, a second flow chart of a robot inspection method based on task scheduling according to the present application may include the following steps:
s201, constructing a loadable task quantity input set of the cabinet.
The loadable task amount input set of the cabinet can comprise the following data:
(1) The cabinet is located in the data room.
The factors such as ventilation and heat dissipation conditions, space limitation, power supply, physical safety and the like of the placement position of the cabinet can influence the load bearing condition of the cabinet, so that the position influence factors of the cabinet need to be considered.
(2) Data center CPU utilization.
The CPU utilization of the data center refers to the measurement of the occupied time and degree of the CPU in the data center in a certain time, and reflects the relation between the processing capacity and the actual load of the data center. If the CPU utilization is too high, problems such as system performance degradation, response time extension and the like may be caused. Conversely, if the CPU utilization is too low, it is indicated that the processing capacity is excessive, and there is a case where resources are wasted.
For most servers in a data center, the CPU utilization of cabinets in a data room is isomorphic, and the IT demand is evenly distributed to each active server, so that the CPU utilization of these servers is the same, as follows:
s i,t ＝μ t /(m t F),i＝1,2,…,m t
wherein s is i,t For CPU utilization, s of the ith server in time period t i,t ∈[0,1]F is the capacity of each server, thenμ t For IT demand in time period t, m t For the number of servers activated in the data center during time period t,/for the number of servers activated in the data center during time period t>Total number of servers in the data center.
To ensure quality of service, a certain capacity margin needs to be considered, as follows:
s i,t ≤1-σ
where σ is the capacity margin of the server.
The data center CPU utilization s during time period t t The method comprises the following steps:
(3) And (5) energy consumption of the cabinet equipment system.
The energy consumption of the equipment system of the cabinet is mainly from the operation of the IT equipment, power supply, air conditioner and other equipment in the cabinet. The energy consumption of IT equipment is dominant, and includes servers, storage devices, network devices, and the like. The power consumption of these devices depends on their performance, power consumption design, and actual load.
The energy consumption model of the server preferably adopts a statistical fitting mode, and the energy consumption p of the activated ith server i,t The method comprises the following steps:
p i,t ＝p idle +(p peak -p idle )s i,t
wherein p is idle For the energy consumption of the server in idle, p peak Is the peak power consumption of the server.
The power consumption p of IT equipment IT,t The method comprises the following steps:
p IT,t ＝m t p i,t ＝m t p idle +(p peak -p idle )μ t /F。
(4) Historical fault data and operating temperature.
Historical fault data for a cabinet indicates frequent equipment failure or unstable operation conditions, which may mean that the load carrying capacity of equipment within the cabinet is problematic. If the operating temperature of the cabinet is too high, it may cause the equipment to overheat, reducing the life and performance of the equipment, and even causing equipment failure. In addition, the high temperature environment may also cause overload protection triggering of the device, making the device unable to withstand additional loads.
In other embodiments of the present application, historical fault data may also be replaced with cabinet real-time status data. Wherein, the real-time state data of the cabinet can be based on real-time monitoring of the sensor, and the state of the cabinet can be monitored by using the real-time sensor data, such as real-time temperature, humidity, fan rotating speed and the like, so as to more accurately predict the loadable task quantity of the cabinet.
It should be noted that, according to the capacity of the data center and the number of servers, the number of servers activated by the data room may satisfy the following constraint:
IT demand μ during time period t t The method comprises the following steps:
μ t ＝a t +d t
wherein a is t For interactive load reaching data center in time period t, d t Is the data center existing load during the time period t.
Assuming that the interactive load to the data center per period of time is less than the total capacity N of the data center, i.e., N > a t . The IT demand for each period should not exceed the data center capacity N as shown in the following equation:
0≤μ t ≤N
number of active servers m t The requirements are as follows:
wherein,Min order to minimize the number of servers to be started,total number of servers in the data center.
S202, setting a preset bearable task quantity threshold.
The calculation formula of the preset bearable task quantity threshold value is as follows:
wherein Y is 1 A threshold value of the bearable task amount is preset; k (K) 1 The cabinet position weight value; w is a weight value determined according to the position of the cabinet in the data machine room, and the larger the bearable task amount of the data cabinet in the communication network is, the larger the W is, and the value range is generally between 0 and 1; k (K) 2 The cabinet performance weight is given; s is a weight value determined according to the data quantity processed by the cabinet in unit time, and the more the data quantity is, the larger the S is; l is a weight value determined according to the importance degree of the data type processed by the cabinet, and the more important the importance degree of the data type is, the larger L is, and the value range of L is generally between 0 and 9.
S203, inputting the loadable task quantity input set into a loadable task quantity prediction model based on an intelligent algorithm to obtain a loadable task quantity prediction result of the cabinet. By comparing the forecast result of the bearable task amount of the cabinet with a preset bearable task amount threshold, the cabinet can be divided into two categories: high load cabinets and low load cabinets.
S204, under the condition that the work amount to be scheduled of the machine room is different, different strategies are adopted to distribute the task amount, and the robot is driven to carry out inspection.
When the work load to be scheduled of the machine room is more:
under the condition that the work load to be scheduled of the machine room is more, tasks are preferentially distributed to the high-load machine cabinet first, and the high-load machine cabinet has higher bearable capacity and processing capacity and can process more tasks. And then the rest tasks are distributed to the nearby low-load cabinets, so that reasonable utilization and load balancing of resources are ensured. The inspection robot inspects from large to small according to the loadable task quantity of the high-load cabinet, and then inspects from large to small according to the task quantity distributed by the nearby low-load cabinet.
When the work load to be scheduled in the machine room is normal:
and the tasks are evenly distributed according to the bearable capacity of the cabinets, so that each cabinet bears approximately the same task amount. The inspection robot performs inspection according to the global inspection route, so that each device can be ensured to be inspected.
When the work load to be scheduled of the machine room is less:
considering that the tasks of the low-load cabinets are less, the processing capacity of the low-load cabinets is not fully utilized, and therefore, the tasks can be intensively distributed to the high-load cabinets. The inspection robot is concentrated in a high-load cabinet area, and the inspection is performed from large to small according to the task allocation amount.
It should be noted that, the machine room to-be-scheduled workload is more, normal or less, a preset lower threshold and a preset upper threshold may be set, if the machine room to-be-scheduled workload is greater than the preset upper threshold, the machine room to-be-scheduled workload is considered more, if the machine room to-be-scheduled workload is less than the preset lower threshold, the machine room to-be-scheduled workload is considered less, and if the machine room to-be-scheduled workload is between the preset upper threshold and the preset lower threshold, the machine room to-be-scheduled workload is considered normal. In practical application, the preset adjustment amount lower threshold and the preset adjustment amount upper threshold can be set according to practical situations, and the application is not limited.
The method comprises the steps of constructing a loadable task quantity input set based on the position of a cabinet in a data machine room in the data machine room, the CPU utilization rate of the data center, the energy consumption of a cabinet equipment system, historical fault data and the running temperature, and sending the loadable task quantity input set into a loadable task quantity prediction model based on an intelligent algorithm to obtain a loadable task quantity prediction result of the cabinet. The cabinet is divided into a high-load cabinet and a low-load cabinet by comparing the forecasting result of the bearable task quantity of the cabinet with a preset bearable task quantity threshold value. Under the condition that more jobs are to be scheduled in the machine room, tasks are preferentially distributed to the high-load machine cabinets, then the rest tasks are distributed to the nearby low-load machine cabinets, and the inspection efficiency of the robot is optimized while reasonable utilization of resources and load balancing are ensured. And when the job to be scheduled in the machine room is at a normal level, adopting an equilibrium allocation strategy. And when the machine room has fewer jobs to be scheduled, the tasks are intensively distributed to the high-load machine cabinet. The input set of the bearable task quantity comprehensively contains factors which can influence the bearable task quantity of the machine room cabinet, so that the accuracy of the bearable task quantity prediction result is high, the bearable task quantity can be dynamically adjusted, and the requirement of automatic real-time inspection of the robot can be met. The machine cabinet is divided into a high-load machine cabinet and a low-load machine cabinet, so that a theoretical basis is provided for an automatic inspection scheduling method of the robot.
As shown in fig. 3, depending on the above-mentioned robot inspection method based on task scheduling, the present application further provides a robot inspection system based on task scheduling, which may include:
the data acquisition module is used for acquiring a loadable task quantity input set of the cabinet;
the prediction module is used for inputting the loadable task quantity input set into the loadable task quantity prediction model to obtain a loadable task quantity prediction result of the cabinet;
the classification module is used for dividing the cabinet into a high-load cabinet and a low-load cabinet according to the forecasting result of the loadable task quantity of the cabinet; the forecast result of the bearable task quantity of the high-load cabinet is higher than a preset bearable task quantity threshold value, and the forecast result of the bearable task quantity of the low-load cabinet is lower than the preset bearable task quantity threshold value;
and the distribution module is used for distributing task amounts to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amounts distributed by the cabinets.
In other embodiments of the robotic inspection system based on task scheduling of the present application, the data acquisition module may include a location acquisition module for acquiring a location of the cabinet in the data room; the utilization rate acquisition module is used for acquiring the CPU utilization rate of the data center; the energy consumption acquisition module is used for acquiring the energy consumption of the equipment system of the cabinet; the fault acquisition module is used for acquiring historical fault data; and the temperature acquisition module is used for acquiring the running temperature.
In other embodiments of the robot inspection system based on task scheduling, the data acquisition module may also include a position acquisition module configured to acquire a position of the cabinet in the data room; the utilization rate acquisition module is used for acquiring the CPU utilization rate of the data center; the energy consumption acquisition module is used for acquiring the energy consumption of the equipment system of the cabinet; the sensor module is used for acquiring historical fault data; and the temperature acquisition module is used for acquiring real-time state data of the cabinet.
In other embodiments of the robotic inspection system based on task scheduling, a model module may be further included for constructing a loadable task amount prediction model.
In addition, under the machine room robot inspection method based on temperature prediction, the application also provides a robot based on task scheduling, which comprises a robot body and a control unit for controlling the movement of the robot body, wherein the control unit stores a computer program, and the computer program realizes the steps of the robot inspection method based on task scheduling when being executed by a processor.
It should be noted that in several embodiments provided in this application, it should be understood that the disclosed system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple modules may be combined or integrated into another device, or some features may be omitted or not performed. The modules described as separate components may or may not be physically separate, and components shown as modules may be one physical unit or multiple physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each module in each embodiment of the present application may be integrated in one processing unit, or each module may exist alone physically, or two or more modules may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
As shown in fig. 4, an electronic device provided in an embodiment of the present application includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the robot inspection method based on task scheduling described in any one of the embodiments above when executing the computer program.
As shown in fig. 5, another electronic device provided in an embodiment of the present application may further include: the input port is connected with the processor and is used for transmitting the multi-mode data acquired by the external acquisition equipment to the processor; the display unit is connected with the processor and used for displaying the processing result of the processor to the outside; and the communication module is connected with the processor and is used for realizing communication between the electronic equipment and the outside. The display unit may be a display panel, a laser scanning display, or the like; communication modes adopted by the communication module include, but are not limited to, mobile high definition link technology (HML), universal Serial Bus (USB), high Definition Multimedia Interface (HDMI), wireless connection: wireless fidelity (WiFi), bluetooth communication, bluetooth low energy communication, ieee802.11s based communication.
The embodiment of the application provides a computer readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the robot inspection method based on task scheduling described in any embodiment are implemented.
The computer readable storage medium referred to in this application includes Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The description of the relevant parts in the robot inspection system, the electronic device and the computer readable storage medium based on task scheduling provided in the embodiments of the present application is please refer to the detailed description of the corresponding parts in the robot inspection method based on task scheduling provided in the embodiments of the present application, and is not repeated here. In addition, the parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of the corresponding technical solutions in the prior art, are not described in detail, so that redundant descriptions are avoided.
The foregoing is merely a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and variations may be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (13)
1. The robot inspection method based on task scheduling is characterized by comprising the following steps:
acquiring a loadable task quantity input set of a cabinet;
inputting the loadable task quantity input set into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of the cabinet;
dividing the cabinet into a high-load cabinet and a low-load cabinet according to the forecasting result of the loadable task quantity of the cabinet; the forecast result of the bearable task quantity of the high-load cabinet is higher than a preset bearable task quantity threshold value, and the forecast result of the bearable task quantity of the low-load cabinet is lower than the preset bearable task quantity threshold value;
and distributing task amounts to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amounts distributed by the cabinets.
2. The robot inspection method based on task scheduling according to claim 1, wherein the loadable task quantity input set comprises: the location of the cabinet in the data room, the CPU utilization of the data center, the equipment system energy consumption of the cabinet, the historical fault data and the running temperature.
3. The robot inspection method based on task scheduling according to claim 2, wherein the method for determining the preset sustainable task quantity threshold comprises:
wherein Y is 1 To preset the threshold value of the bearable task quantity, K 1 The weight value of the cabinet position is W which is determined according to the position of the cabinet in the data machine room, K 2 The machine cabinet performance weight is determined by S, which is the weight determined according to the data quantity processed by the machine cabinet in unit time, and L, which is the weight determined according to the importance degree of the data type processed by the machine cabinet.
4. The method for inspecting a robot based on task scheduling according to claim 3, wherein the allocating task amounts to the high-load cabinet and the low-load cabinet according to the job amounts to be scheduled in the machine room, and inspecting the robot according to the task amounts allocated to the cabinets, comprises:
if the machine room to-be-scheduled workload is greater than the preset scheduling amount upper threshold, the machine room to-be-scheduled workload is distributed to a high-load cabinet, and if the residual machine room to-be-scheduled workload exists, the residual machine room to-be-scheduled workload is distributed to a low-load cabinet around the high-load cabinet; the robot sequentially carries out inspection according to the forecast result of the loadable task quantity of the high-load cabinet from large to small and the work quantity to be scheduled distributed by the low-load cabinet from large to small;
if the work load to be scheduled of the machine room is smaller than the lower threshold value of the preset scheduling amount, the work load to be scheduled of the machine room is distributed to the high-load cabinet; the robots sequentially carry out inspection according to the work load to be scheduled distributed by the high-load cabinet from large to small;
if the work load to be scheduled of the machine room is between the upper threshold value of the preset scheduling amount and the lower threshold value of the preset scheduling amount, the work load to be scheduled of the machine room is evenly distributed between a high-load cabinet and a low-load cabinet; and the robot sequentially patrols and examines each cabinet according to the global patrol route.
5. The robot inspection method based on task scheduling according to claim 4, wherein the method for determining the CPU utilization of the data center comprises:
wherein s is t For data center CPU utilization during time period t,total number of servers in the data center, F is the capacity of each server, mu t Is the IT demand during time period t.
6. The method for robot inspection based on task scheduling according to claim 5, wherein the method for determining the energy consumption of the rack equipment system comprises the following steps:
P IT,t ＝m t p idle +(p peak -p idle )μ t /F
wherein P is IT,t For the energy consumption of the cabinet equipment system in the time period t, m t For the number of active servers in the data center during time period t, p peak P is the peak power consumption of the server idle Is the energy consumption of the server when idle.
7. The robot inspection method based on task scheduling according to claim 1, wherein the loadable task quantity input set comprises: the position of the cabinet in the data machine room, the CPU utilization rate of the data center, the energy consumption of equipment systems of the cabinet, the running temperature and the real-time state data of the cabinet.
8. A robot inspection system based on task scheduling, comprising:
the data acquisition module is used for acquiring a loadable task quantity input set of the cabinet;
the prediction module is used for inputting the loadable task quantity input set into a loadable task quantity prediction model to obtain a loadable task quantity prediction result of the cabinet;
the classification module is used for dividing the cabinet into a high-load cabinet and a low-load cabinet according to the forecasting result of the loadable task quantity of the cabinet; the forecast result of the bearable task quantity of the high-load cabinet is higher than a preset bearable task quantity threshold value, and the forecast result of the bearable task quantity of the low-load cabinet is lower than the preset bearable task quantity threshold value;
and the distribution module is used for distributing task amounts to the high-load cabinet and the low-load cabinet according to the work amount to be scheduled of the machine room, and enabling the robot to carry out inspection according to the task amounts distributed by the cabinets.
9. The robotic inspection system based on task scheduling of claim 8, wherein the data acquisition module comprises:
the position acquisition module is used for acquiring the position of the cabinet in the data machine room;
the utilization rate acquisition module is used for acquiring the CPU utilization rate of the data center;
the energy consumption acquisition module is used for acquiring the energy consumption of the equipment system of the cabinet;
the fault acquisition module is used for acquiring historical fault data;
and the temperature acquisition module is used for acquiring the running temperature.
10. The robotic inspection system based on task scheduling of claim 8, wherein the data acquisition module comprises:
the position acquisition module is used for acquiring the position of the cabinet in the data machine room;
the utilization rate acquisition module is used for acquiring the CPU utilization rate of the data center;
the energy consumption acquisition module is used for acquiring the energy consumption of the equipment system of the cabinet;
the sensor module is used for acquiring historical fault data;
and the temperature acquisition module is used for acquiring real-time state data of the cabinet.
11. A robot based on task scheduling comprises a robot body and a control unit for controlling the movement of the robot body; the robot inspection method according to any one of claims 1 to 7, characterized in that the control unit has stored therein a computer program which, when executed by a processor, realizes the steps of the robot inspection method based on task scheduling.
12. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the robot inspection method based on task scheduling according to any one of claims 1 to 7 when executing the computer program.
13. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, implements the steps of the robot inspection method based on task scheduling according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410124897.2A CN117863199A (en) | 2024-01-29 | 2024-01-29 | Robot based on task scheduling, inspection method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410124897.2A CN117863199A (en) | 2024-01-29 | 2024-01-29 | Robot based on task scheduling, inspection method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117863199A true CN117863199A (en) | 2024-04-12 |
Family
ID=90577448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410124897.2A Pending CN117863199A (en) | 2024-01-29 | 2024-01-29 | Robot based on task scheduling, inspection method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117863199A (en) |
-
2024
- 2024-01-29 CN CN202410124897.2A patent/CN117863199A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8954197B2 (en) | Arrangement for operating a data center using building automation system interface | |
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| JP4724730B2 (en) | Information processing system operation management method, operation management program, operation management apparatus, and information processing system | |
| JP4768082B2 (en) | Information management system operation management device | |
| US20090240964A1 (en) | Method and apparatus for holistic power management to dynamically and automatically turn servers, network equipment and facility components on and off inside and across multiple data centers based on a variety of parameters without violating existing service levels | |
| JP2012506597A (en) | How to achieve recognizable power management | |
| JP5245852B2 (en) | Server processing distribution apparatus, server processing distribution method, and server processing distribution program | |
| EP2277094B1 (en) | Arrangement for operating a data center using building automation system interface | |
| CN109784504A (en) | Data center's long-distance intelligent operation management method and system | |
| CN113708493A (en) | Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment | |
| CN117863199A (en) | Robot based on task scheduling, inspection method and related device | |
| CN113632132A (en) | Computer-aided energy management method and energy management system | |
| CN111045363A (en) | Intelligent operation and maintenance management and control cloud platform of information communication network | |
| CN115899991A (en) | Air conditioner operation control method and device, electronic equipment and storage medium | |
| JP5422729B2 (en) | Information processing system operation management method, operation management program, operation management apparatus, and information processing system | |
| CN114828579B (en) | Energy-saving control method of container data center and related equipment | |
| Tsachouridis et al. | Optimal thermal regulation of a real data centre | |
| CN108050654A (en) | Hospital's air quantity variable air conditioner case efficiency method for early warning, terminal and readable storage medium storing program for executing | |
| Isaev et al. | Data center efficiency model: A new approach and the role of Artificial Intelligence | |
| CN116963457A (en) | Parameter prediction method, device and equipment of thermodynamic equipment and storage medium | |
| CN116664759A (en) | State detection method and system based on holographic data processing substation equipment | |
| CN116775401A (en) | Cloud resource basic performance analysis system | |
| CN116541175A (en) | Big data information processing system and method based on computer | |
| Ruiz-Falcó et al. | Monitoring New Efficiency Metrics: beyond PUE | |
| Hockey et al. | Human-machine design issues in control rooms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |