CN112464309B - Equipment arrangement method for smart city data center - Google Patents
Equipment arrangement method for smart city data center Download PDFInfo
- Publication number
- CN112464309B CN112464309B CN202011329761.3A CN202011329761A CN112464309B CN 112464309 B CN112464309 B CN 112464309B CN 202011329761 A CN202011329761 A CN 202011329761A CN 112464309 B CN112464309 B CN 112464309B
- Authority
- CN
- China
- Prior art keywords
- machine room
- equipment
- room equipment
- gene
- genetic algorithm
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 61
- 230000002068 genetic effect Effects 0.000 claims abstract description 28
- 238000013500 data storage Methods 0.000 claims abstract description 7
- 230000035772 mutation Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010064571 Gene mutation Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
Abstract
The invention discloses a device arrangement method of a smart city data center, which comprises the following steps: step S1, abstracting a plane model of machine room equipment into an abstract polygon in a overlooking state, and inputting the abstract polygon into a template library; step S2, obtaining position information of boundaries of each room of the data center; step S3, identifying the name of the room according to the characteristics of the space by using a depth vision method; and S4, performing machine room equipment arrangement by using a multiple genetic algorithm, wherein the multiple genetic algorithm comprises the steps of obtaining a plurality of first gene code strings distributed by the machine room equipment in each room of the whole data storage equipment by adopting the genetic algorithm, and obtaining a second gene code string distributed by the machine room equipment by adopting the genetic algorithm for the plurality of first gene code strings in each room. The invention rapidly generates the layout scheme of the machine room equipment which accords with the function judgment of the layout rule, the novelty judgment and the priori knowledge in batches.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a device arrangement method of a smart city data center.
Background
Along with the development of computer and network technology, IT devices such as servers and network communication devices are developing toward miniaturization, networking and framing, and various devices such as a plurality of data storage cabinets and heat dissipation devices are required to be placed in a data center machine room of a smart city, which is the core of comprehensive wiring and information network devices and is also a data convergence center of an information network system.
Data storage enclosures have long been regarded as low-value, accessory products containing servers in IT applications and are not appreciated by humans. However, the low-value data storage cabinet is the most direct physical protection of expensive IT equipment, and the importance of the IT equipment is that the IT equipment is neglected in the IT microenvironment, for example, heat management, cable management, cabinet power distribution, compatibility and other advanced performances, the unreasonable arrangement of the cabinet can lead to high failure rate, reduced performance, resource waste and the like of the data storage cabinet of the data center, and only by reasonably planning the equipment layout, the functions of all subsystems can be fully exerted, so that the operation and maintenance personnel can be conveniently expanded in future, the management of the operation and maintenance personnel is facilitated, and the investment is saved.
Disclosure of Invention
To solve the above problems, the present invention provides a device arrangement method of a smart city data center, comprising the steps of: step S1, abstracting a plane model of machine room equipment into an abstract polygon in a overlooking state, and inputting the abstract polygon into a template library; step S2, obtaining position information of boundaries of each room of the data center;
step S3, identifying the name of the room according to the characteristics of the space by using a depth vision method; step S4, performing machine room equipment arrangement by using a multiple genetic algorithm, wherein the multiple genetic algorithm comprises the steps of obtaining a plurality of first gene coding strings allocated to the machine room equipment in each room of the whole data storage equipment by adopting the genetic algorithm, and obtaining a second gene coding string of the layout of the machine room equipment by adopting the genetic algorithm for the plurality of first gene coding strings in each room respectively, and specifically comprises the following steps: step S41, forming a first gene code for each machine room device respectively, and establishing a mapping relation between the machine room device and the genes; step S42, randomly initializing a population, wherein the population comprises a plurality of schemes distributed by machine room equipment, each scheme corresponds to a first gene coding string formed by first gene codes, and each first gene coding string is used as a gene individual in the population in a genetic algorithm; step S43, carrying out fitness scoring on each gene individual by using a first fitness function, and eliminating a machine room equipment allocation scheme lower than a fitness threshold, wherein the first fitness function comprises priori knowledge of machine room equipment allocation; step S44, for the scheme lower than the fitness threshold, performing the iterative loop of S43 and S44 again when the combination crossover and mutation become new first gene coding strings until the fitness threshold is reached; and step S45, generating a plurality of machine room equipment allocation schemes meeting the fitness threshold.
Further, preferably, the method further comprises: and S6, decoding the generated first gene coding string of the layout of the machine room equipment into an abstract polygon of the machine room equipment, inquiring a model library, decoding the second gene coding string into position parameters of the layout of the machine room equipment, and drawing a plane model of the machine room equipment into a plane diagram of the machine room.
The invention adopts multiple genetic algorithms, a plurality of machine room equipment allocation schemes are generated by utilizing the genetic algorithm aiming at the whole data center, genetic algorithm calculation is respectively carried out on each machine room equipment allocation scheme by utilizing the genetic algorithm according to each room, so that the layout schemes of each room are obtained, and the machine room equipment layout schemes which accord with the function judgment of the layout rule, the novelty judgment and the priori knowledge can be quickly generated in batches.
Drawings
The above-mentioned features and technical advantages of the present invention will become more apparent and readily appreciated from the following description of the embodiments thereof, taken in conjunction with the accompanying drawings.
Fig. 1 is a flowchart showing a device arrangement method of a smart city data center according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a data center rack arrangement in accordance with an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art will recognize that the described embodiments may be modified in various different ways, or combinations thereof, without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive in scope. Furthermore, in the present specification, the drawings are not drawn to scale, and like reference numerals denote like parts.
Fig. 1 is a flowchart showing a device arrangement method of a smart city data center according to the present invention. An embodiment of the present invention is described below with reference to fig. 1.
The device arrangement method of the smart city data center of the present embodiment includes the steps of:
Step S1, abstracting a plane model (under overlooking condition) of some common machine room equipment into corresponding abstract polygons, and inputting the abstract polygons into a template library. For example, the planar model of a cube device in plan view is square, and the planar model of a cuboid device is rectangular. Of course this embodiment does not exclude other abstract polygonal forms which may also be more complex.
And S2, obtaining boundary information of the data center machine room. The data center may be an entire room or may be a plurality of connected rooms. The machine room plan can be converted into a gray level graph by using a binarization method, and the boundary of each room is extracted by using a flooding method.
The binarization is to set a gray value threshold value, compare the pixel value of each point of the machine room plane graph with the gray value threshold value, set the pixel value of the pixel point larger than or equal to the gray value threshold value as 255, and set the pixel value of the pixel point smaller than the gray value threshold value as 0, so as to convert the machine room plane graph into the gray graph. The gray value threshold may be a median value selected from 0 to 255.
The flooding method obtains all connected domains (namely areas of all rooms) in the gray level image, and the areas are respectively extracted through marks. The calculation of the connected domain is to check the connectivity of each pixel and its neighboring pixels. One line may be scanned from left to right and then line feed down continues from left to right, and each time a pixel is scanned, the immediately adjacent pixel values of the pixel location, up, down, left, right, up, down, left, right, are examined.
The following specific steps are described by taking up, down, left and right checks as examples:
assuming that the pixel value of the current position is 255, two adjacent pixels to the left and above it are checked (these two pixels must be scanned before the current pixel). The combination of these two pixel values and the label is the following four cases:
1) The pixel values on the left and the upper are 0, and a new mark (which indicates the start of a new connected domain) is given to the pixel at the current position;
2) Only one pixel value at the left side and the upper side is 255, and the pixel at the current position is the same as the pixel with the pixel value of 255 in the marks;
3) The pixel values on the left and the upper are 255 and the marks are the same, and the marks of the pixels at the current position are the same as the marks of the pixels on the left and the upper;
4) The pixel values on the left and the upper are 255 and the marks are different, the smaller mark is assigned to the pixel at the current position, and then the 4 steps are respectively executed after each trace back from the right to the left until the pixel at the beginning of the region is traced back.
The areas of each room can be extracted from the gray scale map through the above 4 steps.
And S3, automatically identifying the space name according to the characteristics of the space (such as floor, flue, azimuth, area and the like) by using a depth vision method, and writing a rule function by combining with a plurality of priori knowledge to correct. For example, the depth vision method employs a neural network model to extract features of a room, and then performs classification recognition, thereby determining a name. The method specifically comprises the following steps:
step S31, a training set and a testing set are established, wherein the training set comprises training pictures and corresponding real labels, each training picture is a top view of some rooms, and the characteristics of each room comprise, for example, the position of a power interface, the window orientation, the room size and the like. The test set contains test images, and the pictures in the test set are predicted through the pictures in the training set.
In step S32, a deep neural network is constructed, which includes an input layer, three hidden layers, and an output layer. The layers are fully connected, and a linear relation exists between the output and the input of each layer, and the j-th neuron of the r-th layer of the deep neural network is expressed as follows:
Wherein the r-1 layer comprises m neurons;
represents the (r-1) th layer of the (k) th neuron/> To/>Weights of (2);
Representation to/> Is offset from (a);
Sigma (·) is the activation function;
w is a linear relationship coefficient;
b is bias;
the output layer adopts a softmax classifier and outputs the index of the neuron with the largest probability value as a prediction result of the neural network on the room picture.
Step S4, performing a room equipment arrangement using a multiple genetic algorithm including a genetic algorithm for obtaining a room equipment allocation of the whole data center room, and a genetic algorithm for a room equipment layout of each room, specifically including the following sub-steps:
step S41, each machine room device (comprising different types, shapes and sizes) is respectively formed into a first gene code, so that a mapping relation between the machine room device and the genes is established.
Step S42, randomly initializing a population, where the population includes a plurality of schemes for assigning machine room devices, each scheme is to assign different machine room devices to each room of the whole data center machine room (but the machine room device layout is not performed yet), each scheme corresponds to a first gene coding string composed of first gene codes, and each first gene coding string may be referred to as a genetic entity in the population in the genetic algorithm.
In step S43, each individual gene is subjected to a fitness evaluation using a first fitness function, where the first fitness function contains some a priori knowledge of the whole set of rooms, for example, a data center typically includes a main room for storing cabinets, a basic workroom (including offices, dressing rooms, etc.), a first type of auxiliary room (including maintenance rooms, instrument rooms, spare parts rooms, storage medium storage rooms, data rooms), a second type of auxiliary room (including low voltage power distribution, UPS power rooms, battery rooms, rooms for precision air conditioning systems, gas fire extinguishing equipment rooms, etc.), and a third type of auxiliary room (including storerooms, general rest rooms, restrooms, etc.).
Depending on the fit of the respective equipment to the respective room, for example, the main machine room usually has a cabinet, an air conditioner, a UPS, a power distribution cabinet, an automatic fire alarm device, etc., the maintenance room usually has corresponding maintenance equipment, and the rest room usually has a bed. And forming judgment conditions by the prior knowledge, forming a first adaptive function, and eliminating cabinet allocation schemes lower than the fitness threshold value through scoring of the first adaptive function. The first fitness function may also be set according to its own preferences as a priori knowledge to make its arrangement more desirable.
Step S44, for the scheme which does not reach the score, combination crossover and mutation are carried out, wherein the combination crossover refers to exchanging one or more genes in one layout with the genes at corresponding positions in the other layout, so as to obtain a new integral first gene coding string. The mutation refers to that a mutation operation is carried out on a gene coding string by using mutation probability and randomly designated gene or genes, so that a new integral gene coding string is formed. The corresponding binary code string is the conversion of 1 and 0 of a certain bit or a certain bits which are randomly designated. For example, after the binary code 01_11_01_10_10_11 is subjected to gene mutation, the binary code may become a new code string 00_11_01_01_10_11, and the new first gene code string is executed again with the S43 and S44 iterative loops, so as to gradually increase the score of the fitness function until the fitness threshold is reached;
Step S45, generating a plurality of machine room equipment allocation schemes meeting the fitness threshold.
Then, in step S5, the parallel calculation is again adopted to evolve by using a genetic algorithm for each room, corresponding to any one of the machine room equipment allocation schemes, and the layout of the machine room equipment is determined. Specifically, the method comprises the following substeps:
In step S51, the genetic code of the genetic algorithm is designed, and the abscissa x, the ordinate y and the rotation angle α of the center of the abstract polygon of the machine room equipment in the room are used as the second genetic code of one machine room equipment, where the abscissa x, the ordinate y and the rotation angle α may be formed by binary codes. The positions of all the machine room devices are respectively formed into second gene codes and are arranged in a row according to the sequence, such as: x1_y1_α1_x2_y2_α2_, xn_yn_αn, forms a second gene-encoded string of the overall machine room equipment layout. The initial values of the x, y and the rotation angle α may be set manually, for example, the initial values of x and y are set so that the boundary between the abstract polygon and the room reaches a set distance, and the initial value of α is set to 0.
For each room, randomly generating a plurality of second gene-encoding strings as an initial population, the second gene-encoding strings expressed as:
wherein vector k m represents the m-th second gene-coding string of the room, The second gene code of the jth machine room device representing the mth second gene code string in the population, and N represents the total number of machine room devices in one room. For example, a second gene coding string may be a cabinet of 24U (1200 mm 600 mm), 32U (160 mm 600 mm), 42U (2000 mm 600 mm) … …, which are sequentially arranged in combination of coordinate and angle information.
Step S52, designing a machine room equipment layout rule function of each space, wherein the machine room equipment layout rule function comprises functional dependency, azimuth constraint and basic specification constraint among each machine room equipment, and the higher score is given by conforming to the specification constraint. For example, the equipment arrangement of the machine room is adapted to the position of a power supply so as to facilitate the laying of strong and weak cables; for example, the same brand of machine room equipment tends to be arranged in the same area, facilitating maintenance operations; for example, the machine room equipment is arranged in a back-to-back and face-to-face manner, so that cold and hot air is effectively separated, and for example, the clear width d of a passage between two rows of machine room equipment is not less than 1.2m.
For the rule function in terms of distance, a distance threshold may be set, for example, the width of the aisle between two columns of cabinets is calculated through the position coordinates of the cabinet 100, and if the width is lower than the set distance threshold, it is determined that the rule Fan Yaoshu is not met. Or the distance between the equipment in the machine room and the wall surface can be determined by a set distance threshold value to determine whether the rule Fan Yaoshu is met. If the distance threshold is exceeded, it is determined that the bar Fan Yaoshu is not met, thereby eliminating a layout scheme.
For orientation constraints, the cabinet should be described in a back-to-back, face-to-face example. Firstly, verifying whether the rotation angles alpha of the cabinets are consistent, and if not, directly eliminating the layout scheme. If so, further judging whether the back-to-back and face-to-face characteristics are met between the cabinets.
Several bits can be added in the second gene code of the cabinet to represent the position coordinates of the front and back sides of the cabinet, and the position coordinates of the front sides of two adjacent cabinets are used for judging whether the prior knowledge is met. For example, for one second gene encoding string x1_y1_α1_a_x2_y2_b_x3_y3_x4_y4_α4_a_x5_y5_b_x6_y6, wherein the second gene encoding x1_y1_α1_a_x2_y2_b_x3_y3 represents the first enclosure, x1_y1_α1 is the coordinates and rotation angle of the center of the first enclosure, a_x2_y2 represents the coordinates of the center of the front of the first enclosure, and b_x3_y3 represents the coordinates of the center of the back of the first enclosure.
X4_y4_α4_a_x5_y5_b_x6_y6 represents the second cabinet, and likewise, x4_y4_α4 represents the center coordinates and rotation angle of the second cabinet. A_x5_y5 represents the coordinates of the center of the front face of the second cabinet, and b_x6_y6 represents the coordinates of the center of the back face of the second cabinet.
Judging whether the two second cabinets are opposite in back or not through the following formula:
Z1＝Q1+Q2+P1
where P1 is the distance between the back sides of the two cabinets,
Z1 is the distance between the two cabinet fronts;
q1 is the width between the front and back of a cabinet;
Q2 is the width between the front and back of another cabinet.
Step S53, designing a novelty function, wherein the novelty function is to give a higher score to a more novel layout mode. The method for judging the novelty is to calculate the novelty by comparing the similarity between the generated layout and the existing and existing layout, and the higher the similarity between the generated layout and the existing layout is, the lower the novelty is, and the specific operation is as follows:
Step S531, extracting the machine room equipment and the orientation of the machine room equipment by identifying the existing indoor layout, and forming a comparison gene library containing a plurality of machine room equipment layouts V1, V2 … and Vn in the form of the second gene codes same as the step S51, wherein V1, V2 … and Vn are respectively second gene code strings;
Step S532, when calculating the novelty of a layout, normalizing the second gene-encoding strings V1, V2 …, vn of the comparison gene library and the second gene-encoding string B of the new layout to be compared, respectively;
In step S533, the azimuth difference vector δ=v1-B is calculated, the degree of difference between the second gene coding string V1 and the second gene coding string B is represented by the norm δ, and similarly, the degree of difference between V2 and An second gene coding string B in a new layout is calculated to obtain the sum of the degrees of difference between B and V1, V2 …, vn, and the higher the sum of the degrees of difference is, the higher the novelty is, the higher the score is given.
In step S54, the above series of machine room equipment layout rule functions and novelty functions are combined with corresponding weights into an adaptive function in a genetic algorithm.
In particular ,f(G)＝E1*G1+E2*G2…Ei*Gi+En-1*Gn-1+En*Gn+E*F
Wherein f (G) is an adaptive function;
G i is the equipment layout rule function of the ith machine room, E i is the weight corresponding to G i, and the weight can be set manually according to preference;
n represents the number of the equipment layout rule functions of the machine room;
F is a novel function; e is the weight corresponding to F.
Thus, for a machine room equipment layout, a score can be obtained by inputting the second gene code string into the fitness function. For each room, a score, i.e., an adaptive score, is obtained for the different layout of the room.
In step S55, it is determined whether the fitness threshold is reached for each room, and if the fitness threshold is reached for each room, the evolution results of each room are combined to form an optimal equipment layout of the machine room, and step S6 is performed. If the fitness of the room does not reach the fitness threshold, the following step S56 is performed.
In step S56, for the rooms which do not reach the fitness threshold, performing combination crossover and mutation, and executing the iterative loop of step S54 and step S55 again on the new second gene coding string, thereby gradually increasing the score of the fitness function until the fitness threshold is reached;
In step S6, the generated first gene code string of the optimal layout of the computer room equipment of each evolution instance is decoded into an abstract polygon of the specific computer room equipment, a model library is queried, the second gene code string is decoded into position parameters of the layout of the computer room equipment, a corresponding plane model is selected and drawn into the computer room plane graph, and a series of corresponding output files are generated.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. A device arrangement method of a smart city data center, comprising the steps of:
Step S1, abstracting a plane model of machine room equipment into an abstract polygon in a overlooking state, and inputting the abstract polygon into a template library;
step S2, obtaining position information of boundaries of each room of the data center;
Step S3, identifying the name of the room according to the characteristics of the space by using a depth vision method;
Step S4, performing machine room equipment arrangement by using a multiple genetic algorithm, wherein the multiple genetic algorithm comprises the steps of obtaining a plurality of first gene coding strings allocated to the machine room equipment in each room of the whole data storage equipment by adopting the genetic algorithm, and obtaining a second gene coding string of the layout of the machine room equipment by adopting the genetic algorithm for the plurality of first gene coding strings in each room respectively, and specifically comprises the following steps:
Step S41, forming a first gene code for each machine room device respectively, and establishing a mapping relation between the machine room device and the genes;
Step S42, randomly initializing a population, wherein the population comprises a plurality of schemes distributed by machine room equipment, each scheme corresponds to a first gene coding string formed by first gene codes, and each first gene coding string is used as a gene individual in the population in a genetic algorithm;
step S43, carrying out fitness scoring on each gene individual by using a first fitness function, and eliminating a machine room equipment allocation scheme lower than a fitness threshold, wherein the first fitness function comprises priori knowledge of machine room equipment allocation;
step S44, for the scheme lower than the fitness threshold, performing the iterative loop of S43 and S44 again when the combination crossover and mutation become new first gene coding strings until the fitness threshold is reached; and
Step S45, generating a plurality of machine room equipment allocation schemes meeting the fitness threshold.
2. The device arrangement method of a smart city data center of claim 1, further comprising:
and S6, decoding the generated first gene coding string of the layout of the machine room equipment into an abstract polygon of the machine room equipment, inquiring a model library, decoding the second gene coding string into position parameters of the layout of the machine room equipment, and drawing a plane model of the machine room equipment into a plane diagram of the machine room.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329761.3A CN112464309B (en) | 2020-11-24 | 2020-11-24 | Equipment arrangement method for smart city data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329761.3A CN112464309B (en) | 2020-11-24 | 2020-11-24 | Equipment arrangement method for smart city data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112464309A CN112464309A (en) | 2021-03-09 |
| CN112464309B true CN112464309B (en) | 2024-04-30 |
Family
ID=74798634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011329761.3A Active CN112464309B (en) | 2020-11-24 | 2020-11-24 | Equipment arrangement method for smart city data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112464309B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115577439B (en) * | 2022-12-08 | 2023-05-12 | 中国电子工程设计院有限公司 | Method and device for generating multi-stage layout of medical process |
| CN116108125B (en) * | 2023-04-17 | 2023-06-16 | 创意信息技术股份有限公司 | City geocoding method, device, equipment and storage medium |
| CN117332697A (en) * | 2023-11-03 | 2024-01-02 | 中国电子产业工程有限公司 | Network security system optimization method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009128979A (en) * | 2007-11-20 | 2009-06-11 | Dainippon Printing Co Ltd | Room arrangement editing apparatus and computer program |
| CN108596403A (en) * | 2018-05-09 | 2018-09-28 | 西南交通大学 | A kind of modeling of workshop multirow layout and method for solving |
| CN109600956A (en) * | 2018-12-10 | 2019-04-09 | 国家电网有限公司信息通信分公司 | A kind of data center server placement location optimization algorithm and system |
| CN110991719A (en) * | 2019-11-25 | 2020-04-10 | 河海大学 | Method for optimizing layout pipe diameters in layering mode for regional heat supply pipe network of intelligent comprehensive energy system |
| CN111324422A (en) * | 2020-02-24 | 2020-06-23 | 武汉轻工大学 | Multi-target virtual machine deployment method, device, equipment and storage medium |
-
2020
- 2020-11-24 CN CN202011329761.3A patent/CN112464309B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009128979A (en) * | 2007-11-20 | 2009-06-11 | Dainippon Printing Co Ltd | Room arrangement editing apparatus and computer program |
| CN108596403A (en) * | 2018-05-09 | 2018-09-28 | 西南交通大学 | A kind of modeling of workshop multirow layout and method for solving |
| CN109600956A (en) * | 2018-12-10 | 2019-04-09 | 国家电网有限公司信息通信分公司 | A kind of data center server placement location optimization algorithm and system |
| CN110991719A (en) * | 2019-11-25 | 2020-04-10 | 河海大学 | Method for optimizing layout pipe diameters in layering mode for regional heat supply pipe network of intelligent comprehensive energy system |
| CN111324422A (en) * | 2020-02-24 | 2020-06-23 | 武汉轻工大学 | Multi-target virtual machine deployment method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于多基因分量编码遗传算法的矩形物体布局问题;徐生菊;王命延;;南昌大学学报(理科版);20070815(第04期);399-403 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112464309A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112464309B (en) | Equipment arrangement method for smart city data center | |
| CN109918532B (en) | Image retrieval method, device, equipment and computer readable storage medium | |
| ES2612328T3 (en) | Methods and systems to manage power and cooling of an installation | |
| US10275683B2 (en) | Clustering-based person re-identification | |
| US11693374B2 (en) | Building system with string mapping based on a sequence to sequence neural network | |
| CN106060008B (en) | A kind of network intrusions method for detecting abnormality | |
| CN109635056B (en) | Power utilization address data processing method and device, computer equipment and storage medium | |
| CN110955970A (en) | Photovoltaic power station layout method and device | |
| CN109038660A (en) | A kind of wind-electricity integration System Reactive Power planing method considering quiet Enhancement of Transient Voltage Stability | |
| US20210373509A1 (en) | Building system with string mapping based on a statistical model | |
| WO2016095068A1 (en) | Pedestrian detection apparatus and method | |
| CN112464312B (en) | Equipment arrangement method for smart city data center | |
| Hahsler et al. | remm: Extensible markov model for data stream clustering in r | |
| CN107862416A (en) | A kind of emergency materials warehouse Optimization Method for Location-Selection based on the uncertain collection of box | |
| CN112949740A (en) | Small sample image classification method based on multilevel measurement | |
| CN114168795B (en) | Building three-dimensional model mapping and storing method and device, electronic equipment and medium | |
| CN112364008A (en) | Equipment portrait construction method for intelligent terminal of power internet of things | |
| CN112464310B (en) | Equipment arrangement method for smart city data center | |
| CN114781688A (en) | Method, device, equipment and storage medium for identifying abnormal data of business expansion project | |
| Wang et al. | The criticality of spare parts evaluating model using artificial neural network approach | |
| Ming et al. | Intelligent approaches to tolerance allocation and manufacturing operations selection in process planning | |
| KR102550014B1 (en) | System and Method for providing early warning to prevent false alarm | |
| CN113157739A (en) | Cross-modal retrieval method and device, electronic equipment and storage medium | |
| CN112464311A (en) | Equipment arrangement method of smart city data center | |
| CN112598089A (en) | Image sample screening method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |