CN117288349A - Machine room cold channel micro-environment monitoring system - Google Patents
Machine room cold channel micro-environment monitoring system Download PDFInfo
- Publication number
- CN117288349A CN117288349A CN202311230248.2A CN202311230248A CN117288349A CN 117288349 A CN117288349 A CN 117288349A CN 202311230248 A CN202311230248 A CN 202311230248A CN 117288349 A CN117288349 A CN 117288349A
- Authority
- CN
- China
- Prior art keywords
- temperature
- machine room
- data
- humidity
- monitoring system
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 34
- 238000001816 cooling Methods 0.000 claims abstract description 25
- 239000000428 dust Substances 0.000 claims abstract description 21
- 230000007613 environmental effect Effects 0.000 claims abstract description 14
- 238000005265 energy consumption Methods 0.000 claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 6
- 238000012706 support-vector machine Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000007726 management method Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 238000012098 association analyses Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 abstract description 4
- 238000010219 correlation analysis Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 18
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004378 air conditioning Methods 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000013475 authorization Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 238000009423 ventilation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K7/00—Constructional details common to different types of electric apparatus
- H05K7/20—Modifications to facilitate cooling, ventilating, or heating
- H05K7/20709—Modifications to facilitate cooling, ventilating, or heating for server racks or cabinets; for data centers, e.g. 19-inch computer racks
- H05K7/20836—Thermal management, e.g. server temperature control
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
- G01K13/02—Thermometers specially adapted for specific purposes for measuring temperature of moving fluids or granular materials capable of flow
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P13/00—Indicating or recording presence, absence, or direction, of movement
- G01P13/02—Indicating direction only, e.g. by weather vane
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Thermal Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Engineering & Computer Science (AREA)
- Dispersion Chemistry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Microelectronics & Electronic Packaging (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Aviation & Aerospace Engineering (AREA)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to a machine room cold channel microenvironment monitoring system, which relates to the technical field of cold channels, wherein a temperature and humidity sensor, an air conditioner temperature sensor and a dust counter are arranged in a machine room, temperature changes and dust grade conditions at different positions in the machine room are monitored, environmental parameter information is collected in real time, a remote access interface is used for monitoring environmental parameters and sensor states of the machine room in real time by calling an API (application program interface), the collected temperature and humidity data, equipment loads, energy consumption and machine room layout are subjected to correlation analysis, the temperature and humidity sensor is connected with an alarm according to temperature data and thermal images provided by the machine room microenvironment monitoring system, an audible alarm mechanism is triggered when the temperature exceeds an upper limit and is lower than a lower limit threshold, alarm information is transmitted to workers in time, a machine room SVM temperature prediction model is constructed by using a support vector machine algorithm based on the collected data, and cooling measures are started before a predicted peak period.
Description
Technical Field
The invention relates to the technical field of cold channels, in particular to a machine room cold channel microenvironment monitoring system.
Background
In informatization construction, the machine room operation is in the core position of information exchange management. However, the types and the number of the devices in the machine room are too many, and due to the lack of a matched management method, the physical environment in the machine room can possibly generate emergency at any time, and once a certain device fails, the threat to data transmission, storage and system operation is formed, so that the operation of the global system can be influenced.
In modern data center and computer lab, send cold wind to the frame front end through cold channel technique directly, effectively keep apart heat source and cold source, monitor the interior environmental parameter of computer lab cold channel, reduce the energy waste, improve the energy efficiency and the thermal management of computer lab.
Disclosure of Invention
The invention aims at the technical problems in the prior art, and provides a machine room cold channel micro-environment monitoring system which directly transmits cold air to the front end of a rack through a cold channel technology, so that a heat source and a cold source are effectively isolated, and the problems in the background art are solved.
The technical scheme for solving the technical problems is as follows: the machine room cold channel microenvironment monitoring system specifically comprises a data acquisition module, a data transmission module, a data analysis module, a thermal management optimization module, an anomaly detection module and a temperature prediction module;
and a data acquisition module: collecting temperature data and dust information at different positions in a machine room, and acquiring the speed and direction of air flow;
and a data transmission module: establishing a safety channel between the cloud platform and the data acquisition equipment to finish data transmission;
and a data analysis module: searching for the relevance between temperature and humidity data and equipment load, energy consumption and machine room layout variables, and finding out the relation between temperature and humidity and other factors;
and a thermal management optimization module: optimizing equipment layout to reduce cooling load of a machine room according to temperature data and thermal images provided by a monitoring system;
an abnormality detection module: detecting an abnormal value of the micro-environment data of the machine room, sending out an alarm and timely transmitting alarm information;
temperature prediction module: and obtaining a time period when the temperature of the machine room reaches a peak according to the temperature prediction model, and starting cooling measures before the predicted peak period.
In a preferred embodiment, the data acquisition module is provided with a temperature and humidity sensor, an air conditioner temperature sensor and a dust counter in the machine room, monitors temperature changes and dust level conditions of different positions in the machine room, and specifically comprises the following contents:
s1, a temperature and humidity sensor: a temperature and humidity sensor is arranged in the machine room and connected with a monitoring system, so that environmental parameters in the machine room are monitored in real time;
s2, an air conditioner temperature sensor: an air conditioner temperature sensor is arranged at a position connecting a cold channel and a hot channel in a machine room, the temperature of cold air of the air conditioner is measured, the change trend and the periodicity of temperature and humidity data are identified through an exponential smoothing method, a line graph of original data and a smooth value is drawn, and the cooling effect of the cold channel is monitored, and the specific steps are as follows:
step 1, initializing: selecting a value of a first data point of the historical data as an initial smoothed value S (1) =y (1);
step 2, carrying out exponential smoothing calculation: setting the observed value as y (1), y (2), y (3), y (t), where t represents the index of time, and for t >1, the smoothed value S (t) is calculated as follows:
S(t)＝α×y(t)+(1-α)×S(t-1)
wherein S (t) represents a smooth value of the current time t, y (t) represents an observed value of the current time t, alpha represents a smooth coefficient, and the value is between 0 and 1;
s3, a dust counter: placing a dust counter in a machine room to monitor the particle quantity in different size ranges in the air in real time, knowing the dust grade condition of the machine room, and ensuring good ventilation of equipment and reducing the generation and scattering of dust by installing a sealing cover on a server and storage equipment;
s4, anemometer: placing an anemometer in the cold channel, measuring the speed and direction of air flow, ensuring that cold air is fully supplied to the front end of the rack, avoiding backflow of hot air, calculating the wind speed by measuring the distance and time of air flowing in unit time, calculating the wind direction angle by using a tangent function, and specifically calculating the wind direction angle by using the following formula:
where V denotes wind speed, d denotes the distance the air flows through, t denotes the time of measurement, and x and y denote the horizontal and vertical components measured by the anemometer, respectively.
In a preferred embodiment, the data transmission module establishes a secure channel by using a secure encryption protocol SSL, transmits the collected data to the cloud platform, and the remote access interface monitors the environmental parameters and the sensor state of the machine room from the cloud platform in real time by calling the API, and specifically includes the following contents:
s1, establishing a safety channel: an encryption channel is established between the cloud platform and the data acquisition equipment by using an SSL certificate, and handshake is carried out between the SSL protocol and the cloud platform, so that the validity of the certificate can be verified in the handshake process, and the identity and the information integrity of both communication parties are ensured;
s2, API call: transmitting the acquired data to a cloud platform, and enabling a remote access interface to monitor environmental parameters and sensor states of a machine room from the cloud platform in real time by calling an API (application program interface), wherein the method specifically comprises the following steps of:
step 1, authentication and authorization: the remote access terminal firstly performs authentication and authorization, verifies identity and authority, and before using an API interface, the terminal needs to provide an identity credential API key which is contained in an API request;
step 2, sending a request: the remote access terminal sends a request to the cloud platform by using an API interface, wherein the request needs to specify related parameters for acquiring the robot data, including data types, query conditions and time ranges;
step 3, data processing: after the cloud platform receives the request, inquiring according to the parameters of the request, and returning the robot data meeting the request conditions;
step 4, returning data: and the cloud platform returns the processed data to the remote access terminal as an API response, and the terminal extracts the required data by analyzing the API response to finish data transmission.
In a preferred embodiment, the data analysis module performs association analysis on the collected temperature and humidity data, equipment load, energy consumption and machine room layout, and determines the association degree and direction between the two variables according to the magnitude and sign of the obtained value of the correlation coefficient, which specifically includes the following steps:
s1, association analysis: substituting humidity, equipment load, energy consumption and machine room layout data into a formula in sequence according to Y variable values, searching for the relevance between variables, and finding out the relation between the temperature and the humidity and other factors, wherein the specific steps are as follows:
step 1, calculating the average value of each variable:
wherein X represents an average temperature, X 1 +X 2 +...+X n Sum data representing temperature, Y represents average humidity, Y 1 +Y 2 +...+Y n Total data representing humidity, n representing the number of samples.
Step 2, covariance is calculated:
where cov (X, Y) represents the covariance of temperature and humidity, X represents the average temperature, Y represents the average humidity, and n represents the number of samples.
Step 3, calculating standard deviation of variables:
wherein std (X) represents the standard deviation of temperature, std (Y) represents the standard deviation of humidity, X represents the average temperature, Y represents the average humidity, and n represents the number of samples.
Step 3, calculating the pearson correlation coefficient:
wherein r (X, Y) represents a temperature and humidity correlation coefficient, X represents an average temperature, Y represents an average humidity, cov (X, Y) represents a covariance of the temperature and the humidity, std (X) represents a standard deviation of the temperature, std (Y) represents a standard deviation of the humidity, and the value range of the correlation coefficient is between-1 and 1, wherein:
the correlation coefficient is close to-1, which indicates that the two variables show strong negative correlation;
the correlation coefficient is close to 1, which means that the two variables show a strong positive correlation;
the correlation coefficient is close to 0, representing the wireless correlation between the two variables;
and carrying out association analysis on the temperature and humidity data, the equipment load, the energy consumption and the machine room layout, and judging the association degree and direction between the two variables according to the numerical value and sign of the obtained correlation coefficient.
In a preferred embodiment, the thermal management optimizing module senses the surface temperatures of different objects by using a thermal imaging camera, and represents the surface temperatures according to different color forms, forms a thermal image, is connected with a monitoring system, and according to temperature data and the thermal image provided by a machine room microenvironment monitoring system, the thermal distribution condition of the machine room is known in detail, hot spot problems are found in time, and the layout of equipment is optimized to improve thermal management, improve energy efficiency and reduce the cooling load of the machine room, and specifically comprises the following steps:
s1, image processing, namely dividing a thermal image into areas with similar temperature characteristics by using a K-means clustering algorithm, processing the thermal image by using an image segmentation technology, and identifying and extracting hot spot areas and areas with higher density in the image, wherein the method specifically comprises the following steps of:
step 1, selecting an initial centroid: randomly selecting K centroids from the data set as initial clustering centers;
step 2, data point allocation: for each data point, the Euclidean distance between the data point and each centroid is calculated, and the data point is allocated to the cluster where the closest centroid is located, and the specific calculation formula is as follows:
wherein P represents a point (x 1 ,x 2 ,....x n ) And point (y) 1 ,y 2 ,...,y n ) Euclidean distance between them; the |X| is the point (X 1 ,x 2 ,....x n ) Euclidean distance to origin;
step 3, updating mass centers: for each cluster, the average of all its data points is calculated to obtain a new centroid position, cluster C contains n data points (x 1 ,y 1 ),(x 2 ,y 2 ),..,(x n ,y n ) The specific calculation formula is as follows:
where avg_x is the average of the longitudes of the data points in cluster C and avg_y is the average of the latitudes of the data points in cluster C;
and 4, repeating the step 2 and the step 3 until a stopping criterion is met, wherein the stopping criterion comprises the following contents:
(1) The maximum iteration times are reached;
(2) The allocation of clusters is no longer changed and the data points no longer switch clusters;
(3) The centroid variation of the cluster is less than a certain threshold;
step 5, outputting a result: obtaining K clusters, each cluster comprising a set of data points, and each data point being associated with a centroid;
s2, optimizing equipment layout: according to the position and the characteristics of the hot spot area and the area with higher equipment density, the equipment layout is re-planned, the equipment is far away from a heat source, the space is arranged among the equipment, the quantity and the capacity of cooling equipment are adjusted, whether additional heat dissipation equipment is needed to be added or not is judged according to the result of a thermal image, the temperature of the hot spot area is reduced, the air conditioning parameters including a temperature set value, a humidity set value and the air speed are adjusted, the air circulation of an air conditioning system is improved, hot air is rapidly discharged out of a machine room, and the cooling effect and the energy utilization rate are improved.
In a preferred embodiment, the abnormality detection module uses a 3 sigma principle method based on statistics to identify an abnormal condition in temperature and humidity data, connects a temperature and humidity sensor with an alarm, triggers an acoustic alarm mechanism when the temperature exceeds an upper limit and is lower than a lower limit threshold, and sounds a beep under the abnormal condition to timely transmit alarm information to staff, and specifically includes the following steps:
s1, abnormality detection: the abnormal condition in the temperature and humidity data is identified by using a 3 sigma principle method based on statistics, and the method specifically comprises the following steps:
step 1, summing the temperature and humidity data, dividing the summed temperature and humidity data by the number of samples to obtain a mean value, wherein a calculation formula of the mean value mu is as follows:
wherein μ represents the mean value, x 1 、x 2 、...、x n And the temperature and humidity data samples are represented, and n represents the total sample number.
Step 2, squaring and summing the difference between each temperature and humidity data sample and the mean value, dividing the sum by the number of samples, and squaring the result to obtain a standard deviation, wherein the standard deviation sigma has the following calculation formula:
wherein sigma represents standard deviation, x i And the temperature and humidity data samples are represented, mu represents the average value, and n represents the total sample number.
Step 3, calculating upper and lower threshold limits: according to the 3 sigma principle, the average value is added with 3 times of standard deviation to be used as an upper limit threshold value, and the average value is subtracted with 3 times of standard deviation to be used as a lower limit threshold value, and the method specifically comprises the following steps:
upper threshold = μ+3σ
Lower threshold = μ -3σ
Step 4, judging abnormal values: comparing the temperature and humidity data sample with a threshold value, and regarding the data points as abnormal values when the data points exceed an upper limit threshold value and are lower than a lower limit threshold value;
s2, abnormal alarm: according to the environmental requirement and the monitoring index, a temperature and humidity sensor is used for monitoring the microenvironment of the machine room and is connected with an alarm, an upper limit threshold and a lower limit threshold are set according to the temperature and humidity, when the temperature exceeds the upper limit and is lower than the lower limit, an abnormal value of the microenvironment data of the machine room is detected, an audible alarm mechanism is triggered, beeping sounds are generated under the abnormal condition, and alarm information is timely transmitted to staff.
In a preferred embodiment, the temperature prediction module divides a data set into a training set and a test set according to a time sequence based on the collected data, performs classification prediction through a decision function, uses a support vector machine algorithm to construct a machine room SVM temperature prediction model, and starts cooling measures before a predicted peak period, and specifically comprises the following steps:
step 1, data representation: dividing the data set into a training set and a test set by adopting time sequence, and marking the training set of m samples, wherein each sample is represented by n-dimensional eigenvectors and is marked as x i I represents the index of the sample, and the label is denoted as y i ，y i ∈{-1,1}；
Step 2, objective function: the objective of the SVM is to find an optimal hyperplane, separate samples of different classes, maximize the interval between the two classes of samples, and obtain optimal hyperplane parameters w and b by solving an objective function, wherein the specific formula is as follows:
wherein w represents a normal vector of the decision boundary, b represents an intercept, n represents the number of samples, C represents a penalty parameter, and the penalty degree of error classification is controlled.
Step 3, decision function: the SVM carries out classification prediction through a decision function, and the specific formula is as follows:
f(x)＝sign(w·x+b)
wherein f (x) represents a prediction class, sign represents a sign function, the positive class is +1, and the negative class is-1.
Step 4, predicting peak time: according to the prediction model, calculating a prediction result to obtain a time period when the temperature of the machine room reaches a peak, starting cooling measures before the predicted peak period, adjusting parameters of an air conditioning system, starting a cooling mode, and keeping the temperature in a proper range.
The beneficial effects of the invention are as follows: the temperature and humidity sensor, the air conditioner temperature sensor and the dust counter are installed in the machine room, temperature changes and dust level conditions of different positions in the machine room are monitored, environmental parameter information is collected in real time, a remote access interface is used for calling an API (application program interface), environmental parameters and sensor states of the machine room are monitored in real time, collected temperature and humidity data, equipment load, energy consumption and machine room layout are subjected to correlation analysis, hot spot problems are found in time according to temperature data and thermal images provided by a machine room micro-environment monitoring system, the temperature and humidity sensor is connected with an alarm, when the temperature exceeds an upper limit and is lower than a lower limit threshold, a sound alarm mechanism is triggered, beeps are emitted under abnormal conditions, alarm information is timely transmitted to workers, a machine room SVM temperature prediction model is built based on the collected data, cooling measures are started before a predicted peak period, the equipment failure rate is reduced, and the service life of equipment is prolonged.
Drawings
FIG. 1 is a system flow diagram of the present invention;
fig. 2 is a block diagram of the structure of the present invention.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present application, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "for example" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
Example 1
The embodiment provides a machine room cold channel microenvironment monitoring system as shown in fig. 1-2, which specifically comprises a data acquisition module, a data transmission module, a data analysis module, a thermal management optimization module, an anomaly detection module and a temperature prediction module;
and a data acquisition module: collecting temperature data and dust information at different positions in a machine room, and acquiring the speed and direction of air flow;
and a data transmission module: establishing a safety channel between the cloud platform and the data acquisition equipment to finish data transmission;
and a data analysis module: searching for the relevance between temperature and humidity data and equipment load, energy consumption and machine room layout variables, and finding out the relation between temperature and humidity and other factors;
and a thermal management optimization module: optimizing equipment layout to reduce cooling load of a machine room according to temperature data and thermal images provided by a monitoring system;
an abnormality detection module: detecting an abnormal value of the micro-environment data of the machine room, sending out an alarm and timely transmitting alarm information;
temperature prediction module: and obtaining a time period when the temperature of the machine room reaches a peak according to the temperature prediction model, and starting cooling measures before the predicted peak period.
In this embodiment, what needs to be specifically explained is the data acquisition module, data acquisition module installs temperature and humidity sensor, air conditioner temperature sensor and dust counter in the computer lab, monitors the temperature variation and the dust level condition in the different positions in the computer lab, specifically includes following:
s1, a temperature and humidity sensor: a temperature and humidity sensor is arranged in the machine room and connected with a monitoring system, so that environmental parameters in the machine room are monitored in real time;
s2, an air conditioner temperature sensor: an air conditioner temperature sensor is arranged at a position connecting a cold channel and a hot channel in a machine room, the temperature of cold air of the air conditioner is measured, the change trend and the periodicity of temperature and humidity data are identified through an exponential smoothing method, a line graph of original data and a smooth value is drawn, and the cooling effect of the cold channel is monitored, and the specific steps are as follows:
step 1, initializing: selecting a value of a first data point of the historical data as an initial smoothed value S (1) =y (1);
step 2, carrying out exponential smoothing calculation: setting the observed value as y (1), y (2), y (3), y (t), where t represents the index of time, and for t >1, the smoothed value S (t) is calculated as follows:
S(t)＝α×y(t)+(1-α)×S(t-1)
wherein S (t) represents a smooth value of the current time t, y (t) represents an observed value of the current time t, alpha represents a smooth coefficient, and the value is between 0 and 1;
s3, a dust counter: placing a dust counter in a machine room to monitor the particle quantity in different size ranges in the air in real time, knowing the dust grade condition of the machine room, and ensuring good ventilation of equipment and reducing the generation and scattering of dust by installing a sealing cover on a server and storage equipment;
s4, anemometer: placing an anemometer in the cold channel, measuring the speed and direction of air flow, ensuring that cold air is fully supplied to the front end of the rack, avoiding backflow of hot air, calculating the wind speed by measuring the distance and time of air flowing in unit time, calculating the wind direction angle by using a tangent function, and specifically calculating the wind direction angle by using the following formula:
where V denotes wind speed, d denotes the distance the air flows through, t denotes the time of measurement, and x and y denote the horizontal and vertical components measured by the anemometer, respectively.
In this embodiment, a specific description is provided of a data transmission module, where the data transmission module uses a secure encryption protocol SSL to establish a secure channel, transmits collected data to a cloud platform, and monitors environmental parameters and sensor states of a machine room in real time from the cloud platform by calling an API through a remote access interface, and specifically includes the following contents:
s1, establishing a safety channel: an encryption channel is established between the cloud platform and the data acquisition equipment by using an SSL certificate, and handshake is carried out between the SSL protocol and the cloud platform, so that the validity of the certificate can be verified in the handshake process, and the identity and the information integrity of both communication parties are ensured;
s2, API call: transmitting the acquired data to a cloud platform, and enabling a remote access interface to monitor environmental parameters and sensor states of a machine room from the cloud platform in real time by calling an API (application program interface), wherein the method specifically comprises the following steps of:
step 1, authentication and authorization: the remote access terminal firstly performs authentication and authorization, verifies identity and authority, and before using an API interface, the terminal needs to provide an identity credential API key which is contained in an API request;
step 2, sending a request: the remote access terminal sends a request to the cloud platform by using an API interface, wherein the request needs to specify related parameters for acquiring the robot data, including data types, query conditions and time ranges;
step 3, data processing: after the cloud platform receives the request, inquiring according to the parameters of the request, and returning the robot data meeting the request conditions;
step 4, returning data: and the cloud platform returns the processed data to the remote access terminal as an API response, and the terminal extracts the required data by analyzing the API response to finish data transmission.
In this embodiment, a specific description is provided of a data analysis module, where the data analysis module performs association analysis on collected temperature and humidity data, equipment load, energy consumption, and machine room layout, and determines association degree and direction between two variables according to the magnitude and sign of the obtained correlation coefficient, where the specific contents are as follows:
s1, association analysis: substituting humidity, equipment load, energy consumption and machine room layout data into a formula in sequence according to Y variable values, searching for the relevance between variables, and finding out the relation between the temperature and the humidity and other factors, wherein the specific steps are as follows:
step 1, calculating the average value of each variable:
wherein the method comprises the steps ofX represents an average temperature, X 1 +X 2 +...+X n Sum data representing temperature, Y represents average humidity, Y 1 +Y 2 +...+Y n Total data representing humidity, n representing the number of samples.
Step 2, covariance is calculated:
where cov (X, Y) represents the covariance of temperature and humidity, X represents the average temperature, Y represents the average humidity, and n represents the number of samples.
Step 3, calculating standard deviation of variables:
wherein std (X) represents the standard deviation of temperature, std (Y) represents the standard deviation of humidity, X represents the average temperature, Y represents the average humidity, and n represents the number of samples.
Step 3, calculating the pearson correlation coefficient:
wherein r (X, Y) represents a temperature and humidity correlation coefficient, X represents an average temperature, Y represents an average humidity, cov (X, Y) represents a covariance of the temperature and the humidity, std (X) represents a standard deviation of the temperature, std (Y) represents a standard deviation of the humidity, and the value range of the correlation coefficient is between-1 and 1, wherein:
the correlation coefficient is close to-1, which indicates that the two variables show strong negative correlation;
the correlation coefficient is close to 1, which means that the two variables show a strong positive correlation;
the correlation coefficient is close to 0, representing the wireless correlation between the two variables;
and carrying out association analysis on the temperature and humidity data, the equipment load, the energy consumption and the machine room layout, and judging the association degree and direction between the two variables according to the numerical value and sign of the obtained correlation coefficient.
In this embodiment, a specific description is provided of a thermal management optimization module, where the thermal management optimization module senses surface temperatures of different objects by using a thermal imaging camera, and represents the surface temperatures according to different color forms, forms a thermal image, connects with a monitoring system, and according to temperature data and the thermal image provided by a machine room microenvironment monitoring system, knows the heat distribution situation of the machine room in detail, finds out existing hot spot problems in time, optimizes equipment layout to improve thermal management, improves energy efficiency, and reduces cooling load of the machine room, and specifically includes the following:
s1, image processing, namely dividing a thermal image into areas with similar temperature characteristics by using a K-means clustering algorithm, processing the thermal image by using an image segmentation technology, and identifying and extracting hot spot areas and areas with higher density in the image, wherein the method specifically comprises the following steps of:
step 1, selecting an initial centroid: randomly selecting K centroids from the data set as initial clustering centers;
step 2, data point allocation: for each data point, the Euclidean distance between the data point and each centroid is calculated, and the data point is allocated to the cluster where the closest centroid is located, and the specific calculation formula is as follows:
wherein P represents a point (x 1 ,x 2 ,....x n ) And point (y) 1 ,y 2 ,...,y n ) Euclidean distance between them; the X is the point(x 1 ,x 2 ,....x n ) Euclidean distance to origin;
step 3, updating mass centers: for each cluster, the average of all its data points is calculated to obtain a new centroid position, cluster C contains n data points (x 1 ,y 1 ),(x 2 ,y 2 ),..,(x n ,y n ) The specific calculation formula is as follows:
where avg_x is the average of the longitudes of the data points in cluster C and avg_y is the average of the latitudes of the data points in cluster C;
and 4, repeating the step 2 and the step 3 until a stopping criterion is met, wherein the stopping criterion comprises the following contents:
(1) The maximum iteration times are reached;
(2) The allocation of clusters is no longer changed and the data points no longer switch clusters;
(3) The centroid variation of the cluster is less than a certain threshold;
step 5, outputting a result: obtaining K clusters, each cluster comprising a set of data points, and each data point being associated with a centroid;
s2, optimizing equipment layout: according to the position and the characteristics of the hot spot area and the area with higher equipment density, the equipment layout is re-planned, the equipment is far away from a heat source, the space is arranged among the equipment, the quantity and the capacity of cooling equipment are adjusted, whether additional heat dissipation equipment is needed to be added or not is judged according to the result of a thermal image, the temperature of the hot spot area is reduced, the air conditioning parameters including a temperature set value, a humidity set value and the air speed are adjusted, the air circulation of an air conditioning system is improved, hot air is rapidly discharged out of a machine room, and the cooling effect and the energy utilization rate are improved.
In this embodiment, an abnormality detection module is specifically described, where the abnormality detection module uses a 3 sigma principle method based on statistics to identify an abnormal condition in temperature and humidity data, connects a temperature and humidity sensor with an alarm, and triggers an acoustic alarm mechanism when the temperature exceeds an upper limit and is lower than a lower limit threshold, and sounds a beep under the abnormal condition to timely transmit alarm information to staff, and specifically includes the following contents:
s1, abnormality detection: the abnormal condition in the temperature and humidity data is identified by using a 3 sigma principle method based on statistics, and the method specifically comprises the following steps:
step 1, summing the temperature and humidity data, dividing the summed temperature and humidity data by the number of samples to obtain a mean value, wherein a calculation formula of the mean value mu is as follows:
wherein x is 1 、x 2 、...、x n And the temperature and humidity data samples are represented, and n represents the total sample number.
Step 2, squaring and summing the difference between each temperature and humidity data sample and the mean value, dividing the sum by the number of samples, and squaring the result to obtain a standard deviation, wherein the standard deviation sigma has the following calculation formula:
wherein x is i And the temperature and humidity data samples are represented, mu represents the average value, and n represents the total sample number.
Step 3, calculating upper and lower threshold limits: according to the 3 sigma principle, the average value is added with 3 times of standard deviation to be used as an upper limit threshold value, and the average value is subtracted with 3 times of standard deviation to be used as a lower limit threshold value, and the method specifically comprises the following steps:
upper threshold = μ+3σ
Lower threshold = μ -3σ
Step 4, judging abnormal values: comparing the temperature and humidity data sample with a threshold value, and regarding the data points as abnormal values when the data points exceed an upper limit threshold value and are lower than a lower limit threshold value;
s2, abnormal alarm: according to the environmental requirement and the monitoring index, a temperature and humidity sensor is used for monitoring the microenvironment of the machine room and is connected with an alarm, an upper limit threshold and a lower limit threshold are set according to the temperature and humidity, when the temperature exceeds the upper limit and is lower than the lower limit, an abnormal value of the microenvironment data of the machine room is detected, an audible alarm mechanism is triggered, beeping sounds are generated under the abnormal condition, and alarm information is timely transmitted to staff.
In this embodiment, a specific description is provided of a temperature prediction module, where the temperature prediction module divides a data set into a training set and a test set according to a time sequence based on collected data, performs classification prediction through a decision function, and constructs a machine room SVM temperature prediction model by using a support vector machine algorithm, and specifically includes the following steps:
step 1, data representation: dividing the data set into a training set and a test set by adopting time sequence, and marking the training set of m samples, wherein each sample is represented by n-dimensional eigenvectors and is marked as x i I represents the index of the sample, and the label is denoted as y i ，y i ∈{-1,1}；
Step 2, objective function: the objective of the SVM is to find an optimal hyperplane, separate samples of different classes, maximize the interval between the two classes of samples, and obtain optimal hyperplane parameters w and b by solving an objective function, wherein the specific formula is as follows:
wherein w represents a normal vector of the decision boundary, b represents an intercept, n represents the number of samples, C represents a penalty parameter, and the penalty degree of error classification is controlled.
Step 3, decision function: the SVM carries out classification prediction through a decision function, and the specific formula is as follows:
f(x)＝sign(w·x+b)
wherein f (x) represents a prediction class, sign represents a sign function, the positive class is +1, and the negative class is-1.
Step 4, predicting peak time: according to the prediction model, calculating a prediction result to obtain a time period when the temperature of the machine room reaches a peak, starting cooling measures before the predicted peak period, adjusting parameters of an air conditioning system, starting a cooling mode, and keeping the temperature in a proper range.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (8)
1. The machine room cold channel microenvironment monitoring system is characterized by comprising a data acquisition module, a data transmission module, a data analysis module, a thermal management optimization module, an anomaly detection module and a temperature prediction module;
and a data acquisition module: collecting temperature data and dust information at different positions in a machine room, and acquiring the speed and direction of air flow;
and a data transmission module: establishing a safety channel between the cloud platform and the data acquisition equipment to finish data transmission;
and a data analysis module: searching for the relevance between temperature and humidity data and equipment load, energy consumption and machine room layout variables, and finding out the relation between temperature and humidity and other factors;
and a thermal management optimization module: optimizing equipment layout to reduce cooling load of a machine room according to temperature data and thermal images provided by a monitoring system;
an abnormality detection module: detecting an abnormal value of the micro-environment data of the machine room, sending out an alarm and timely transmitting alarm information;
temperature prediction module: and obtaining a time period when the temperature of the machine room reaches a peak according to the temperature prediction model, and starting cooling measures before the predicted peak period.
2. The machine room cold aisle microenvironment monitoring system according to claim 1, wherein: the data acquisition module monitors temperature change and dust level conditions of different positions in the machine room according to acquired temperature data and dust information, draws a line graph of original data and smooth values, monitors the cooling effect of a cold channel, and calculates the wind speed by measuring the distance and time of air flowing in unit time, wherein the specific calculation formula is as follows:
where V denotes wind speed, d denotes the distance the air flows through, t denotes the time of measurement, and x and y denote the horizontal and vertical components measured by the anemometer, respectively.
3. The machine room cold aisle microenvironment monitoring system according to claim 2, wherein: the method comprises the steps of monitoring the cooling effect of a cold channel, identifying the change trend and periodicity of temperature and humidity data through an exponential smoothing method, drawing a line graph of original data and a smooth value, monitoring the cooling effect of the cold channel, and starting an air conditioner in advance to reduce the temperature, wherein a specific calculation formula is as follows:
S(t)＝α×y(t)+(1-α)×S(t-1)
where S (t) represents a smoothed value at the current time t, y (t) represents an observed value at the current time t, α represents a smoothing coefficient, and a value between 0 and 1 is taken.
4. The machine room cold channel microenvironment monitoring system according to claim 1, wherein the data transmission module establishes a secure channel by using a secure encryption protocol SSL, transmits collected data to a cloud platform, and the remote access interface monitors environmental parameters and sensor states of the machine room from the cloud platform in real time by calling an API.
5. The machine room cold channel microenvironment monitoring system according to claim 1, wherein the data analysis module performs association analysis on temperature and humidity data, equipment load, energy consumption and machine room layout, and finds a relation between temperature and humidity and other factors, and a specific calculation formula is as follows:
where r (X, Y) represents a temperature and humidity correlation coefficient, X represents an average temperature, Y represents an average humidity, cov (X, Y) represents a covariance of the temperature and the humidity, std (X) represents a standard deviation of the temperature, and std (Y) represents a standard deviation of the humidity.
6. The machine room cold channel microenvironment monitoring system according to claim 1, wherein the thermal management optimization module processes the thermal image by using an image segmentation technology, timely finds hot spot problems according to temperature data and the thermal image provided by the machine room microenvironment monitoring system, optimizes equipment layout to improve thermal management, and specifically comprises the following calculation formula:
wherein P represents a point (x 1 ,x 2 ,....x n ) And point (y) 1 ,y 2 ,...,y n ) Euclidean distance between them; the |X| is the point (X 1 ,x 2 ,....x n ) Euclidean distance to origin.
7. The machine room cold channel microenvironment monitoring system according to claim 1, wherein the abnormality detection module uses a 3 sigma principle method based on statistics to identify abnormal conditions in temperature and humidity data, connects a temperature and humidity sensor with an alarm, triggers an acoustic alarm mechanism when the temperature exceeds an upper limit and is lower than a lower limit threshold, and sends out beeping sounds under abnormal conditions to timely transmit alarm information to staff, wherein a specific calculation formula is as follows:
wherein sigma represents standard deviation, x i And the temperature and humidity data samples are represented, mu represents the average value, and n represents the total sample number.
8. The machine room cold channel microenvironment monitoring system according to claim 1, wherein the temperature prediction module is configured to divide a data set into a training set and a test set according to a time sequence based on the collected data, perform classification prediction through a decision function, construct a machine room SVM temperature prediction model by using a support vector machine algorithm, and start a cooling measure before a predicted peak period, wherein a specific calculation formula is as follows:
maximum geometric spacing:
wherein w represents a normal vector of the decision boundary, b represents an intercept, n represents the number of samples, C represents a penalty parameter, and the penalty degree of error classification is controlled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311230248.2A CN117288349A (en) | 2023-09-21 | 2023-09-21 | Machine room cold channel micro-environment monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311230248.2A CN117288349A (en) | 2023-09-21 | 2023-09-21 | Machine room cold channel micro-environment monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117288349A true CN117288349A (en) | 2023-12-26 |
Family
ID=89256485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311230248.2A Pending CN117288349A (en) | 2023-09-21 | 2023-09-21 | Machine room cold channel micro-environment monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117288349A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743975A (en) * | 2024-02-21 | 2024-03-22 | 君研生物科技(山西)有限公司 | Hillside cultivated land soil environment improvement method |
-
2023
- 2023-09-21 CN CN202311230248.2A patent/CN117288349A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743975A (en) * | 2024-02-21 | 2024-03-22 | 君研生物科技(山西)有限公司 | Hillside cultivated land soil environment improvement method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117288349A (en) | Machine room cold channel micro-environment monitoring system | |
| CN107750323B (en) | Method for controlling start of air conditioner and apparatus thereof | |
| CN109375994B (en) | Data center task temperature prediction and scheduling method based on RBF neural network | |
| US20120166007A1 (en) | Method and system for integral energy management of buildings | |
| WO2020039430A1 (en) | Method and system for hvac inefficiency prediction using household electrical smart meter data | |
| US11566809B2 (en) | Occupant thermal comfort inference using body shape information | |
| CN103916860B (en) | Outlier data detection method based on space time correlation in wireless senser cluster l network | |
| CN117113729B (en) | Digital twinning-based power equipment online state monitoring system | |
| CN116909339B (en) | Intelligent household safety early warning method and system based on artificial intelligence | |
| CN114610559A (en) | Equipment operation environment evaluation method, judgment model training method and electronic equipment | |
| CN114383864A (en) | Fault detection method, device, equipment and medium | |
| CN107145986B (en) | Charging electric quantity prediction method and device | |
| CN116546438B (en) | Building monitoring system based on Bluetooth MESH network | |
| KR102433598B1 (en) | A System and Method for Deriving Data Boundary | |
| CN113932282B (en) | Urban heating supervision method and system | |
| CN111862557B (en) | Household accident handling method based on Internet of things monitoring mode | |
| CN117052708A (en) | Intelligent management device and method for cooling fan | |
| CN115861364B (en) | Site personnel management and control method and system based on AI identification | |
| JP2020139665A (en) | Dirt prediction system | |
| JP7340747B2 (en) | Control method, control program and air conditioning control device | |
| CN115546710A (en) | Method, device and equipment for locating personnel in hydraulic power plant and readable storage medium | |
| CN113137726A (en) | Method for regulating and controlling energy equipment in base station machine room | |
| JP2020139705A (en) | Operation control method, operation control program and operation control device | |
| CN110913662A (en) | Management method and device for data center, electronic equipment and medium | |
| CN117376535B (en) | Intelligent campus security control method and system |
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 |