Machine room robot based on temperature prediction, inspection method and related device

Abstract

The application provides a machine room robot based on temperature prediction, a method for inspection and related devices. Temperature-related parameter data of a machine room is obtained, the temperature-related parameter data is input into a cabinet temperature prediction model, temperature prediction results of each cabinet in the machine room are obtained, each cabinet is divided into a high-temperature early warning state, a low-temperature early warning state and a normal state according to the temperature prediction results of each cabinet, the machine room robot inspects the cabinets in the high-temperature early warning state from high to low according to the temperature prediction results, inspects the cabinets in the low-temperature early warning state from low to high according to the temperature prediction results, and inspects the cabinets in the normal state according to the path with the shortest time consumption. The efficiency and pertinence of machine room inspection can be effectively improved.

Description

Technical Field

[0001] This application pertains to robot inspection methods, specifically involving a computer room robot based on temperature prediction, an inspection method, and related devices. Background Technology

[0002] The era of big data and cloud computing has driven the rapid expansion of data center scale. Research shows that domestic data centers consume over 1.5% of the total electricity consumption of society annually, and up to 10% of server racks operate above the permissible temperature range for equipment reliability. Abnormal server rack temperatures negatively impact equipment performance and reliability; high temperatures can lead to overheating, reduced performance, shortened lifespan, and even equipment damage. Therefore, timely monitoring and handling of abnormal server rack temperatures is crucial for ensuring normal equipment operation and maintaining a healthy data center environment. Temperature monitoring and prediction are essential for preventing server overheating and shutdowns, and for improving data center energy efficiency. Robotic inspection not only offers the flexibility and intelligence of manual inspection but also avoids potential omissions, misreadings, and misrecordings, reducing labor costs and improving inspection quality and efficiency.

[0003] With the development of machine learning algorithms, much technical support has been provided for robotic inspection, and many studies have proposed improved inspection methods. For example, Chinese invention patent application CN113858162A proposes a data center inspection robot based on a BP neural network. However, the initial threshold and weights of the BP neural network are randomly generated by the system, which can easily get stuck in local minima due to the uncertainty of the search direction, and then stop searching. Chinese invention patent CN114136436A proposes a big data inspection system and method for power transmission towers based on ESFK and BP algorithms. However, there are problems of inaccurate prediction and delay. Temperature prediction may be affected by various factors, such as changes in the external environment and equipment failure. If the prediction is inaccurate, the robot's inspection route adjustment may lead to incorrect decisions, and may even cause damage to the equipment in the data center. In addition, even if an efficient algorithm is used for temperature prediction, real-time performance may be limited. If the predicted data arrives late, the robot's inspection route may not be adjusted in time, which will affect the monitoring and maintenance of the data center equipment. Summary of the Invention

[0004] This application addresses the technical problems of data center inspection robots being unable to predict faults in advance and having low inspection efficiency by providing a data center robot based on temperature prediction, an inspection method, and related devices, which can effectively improve the efficiency and targeting of data center inspections.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application proposes a data center robot inspection method based on temperature prediction, including:

[0007] Obtain temperature-related parameter data for the computer room;

[0008] Input the temperature correlation parameter data into the rack temperature prediction model to obtain the temperature prediction results of each rack in the computer room;

[0009] Based on the temperature prediction results of each cabinet, the cabinets are divided into high temperature warning state, low temperature warning state, and normal state. The temperature prediction result of the cabinet in the high temperature warning state is higher than the preset high temperature threshold, the temperature prediction result of the cabinet in the low temperature warning state is lower than the preset low temperature threshold, and the temperature prediction result of the cabinet in the normal state is between the preset high temperature threshold and the preset low temperature threshold.

[0010] The data center robot inspects cabinets under high temperature warning from high to low according to the temperature prediction results, cabinets under low temperature warning from low to high according to the temperature prediction results, and cabinets under normal conditions are inspected using the shortest path.

[0011] Preferably, the step of acquiring the temperature-related parameter data of the computer room further includes:

[0012] The K-means clustering algorithm was used to preprocess the temperature-related parameter data of the computer room to obtain preprocessed data;

[0013] The preprocessed data is then standardized.

[0014] Preferably, the standardization process for the preprocessed data includes:

[0015] The data in each category after clustering the preprocessed data are assigned the same weight, and the data in each category are mapped to the same range of change.

[0016] Preferably, the cabinet temperature prediction model includes:

[0017] A BP neural network model optimized using a genetic algorithm.

[0018] Preferably, it further includes:

[0019] Using the threshold and weights of the initial population of the BP neural network model as the optimization target, we optimized it using the GA toolbox provided by MATLAB through a genetic algorithm.

[0020] Preferably, the BP neural network model includes:

[0021] The input layer, hidden layer, and output layer are connected in sequence, with the output layer having 1 node and the hidden layer having 2N+1 nodes; where N is the number of nodes in the input layer.

[0022] Preferably, the temperature-related parameter data of the computer room includes: the number of servers in the computer room, the power consumption of the server racks, the external ambient temperature of the computer room, the internal temperature of the computer room, and the power of the air conditioning equipment in the computer room.

[0023] Secondly, this application proposes a computer room robot inspection system based on temperature prediction, comprising:

[0024] The data acquisition module is used to acquire temperature-related parameter data for the computer room.

[0025] The prediction module is used to input temperature-related parameter data into the rack temperature prediction model to obtain the temperature prediction results of each rack in the computer room.

[0026] The classification module is used to classify the cabinets into high temperature warning state, low temperature warning state and normal state according to the temperature prediction results of each cabinet. The temperature prediction result of the cabinet in the high temperature warning state is higher than the preset high temperature threshold, the temperature prediction result of the cabinet in the low temperature warning state is lower than the preset low temperature threshold, and the temperature prediction result of the cabinet in the normal state is between the preset high temperature threshold and the preset low temperature threshold.

[0027] The control module enables the data center robot to inspect cabinets under high temperature warning from high to low according to the temperature prediction results, cabinets under low temperature warning from low to high according to the temperature prediction results, and cabinets under normal conditions to inspect according to the shortest path.

[0028] Preferably, it further includes: a preprocessing module and a standardization processing module;

[0029] The preprocessing module is used to preprocess the temperature-related parameter data of the computer room using the K-means clustering algorithm to obtain preprocessed data;

[0030] The standardization processing module is used to standardize the preprocessed data.

[0031] Thirdly, this application proposes a temperature-predictive-based computer room robot, including a robot body and a control unit for controlling the movement of the robot body; the control unit stores a computer program, and when the computer program is executed by a processor, it implements the steps of the above-mentioned temperature-predictive-based computer room robot inspection method.

[0032] Fourthly, this application proposes an electronic device comprising:

[0033] Memory, used to store computer programs;

[0034] A processor is used to implement the steps of the above-described temperature-prediction-based computer room robot inspection method when executing the computer program.

[0035] Fifthly, this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described temperature-prediction-based computer room robot inspection method.

[0036] Compared with the prior art, this application has the following beneficial effects:

[0037] This application proposes a data center robot inspection method based on temperature prediction. By simply acquiring temperature-related parameter data of the data center, the method can obtain the temperature prediction results for each rack within the data center through a rack temperature prediction model. Based on the temperature prediction results for each rack, the racks are divided into high-temperature warning state, low-temperature warning state, and normal state. The data center robot then performs inspections on racks in different states. First, predicting rack temperatures using a rack temperature prediction model reduces the possibility of misjudgments and omissions, improving prediction accuracy. Real-time predictions can also be made based on the real-time temperature-related parameter data of the data center, enabling the data center robot to quickly respond to temperature anomalies and take timely inspection measures, effectively reducing the impact of temperature anomalies on equipment. Second, the data center robot can adjust its inspection route and priority at any time based on the prediction results, enabling targeted inspection of racks in high-temperature or low-temperature warning states, improving inspection efficiency and accuracy. Finally, by predicting rack temperatures, the data center robot can help detect temperature anomalies in advance, avoiding damage and malfunctions caused by overheating or overcooling of equipment, helping to reduce maintenance and replacement costs and extend equipment lifespan.

[0038] This application also proposes a temperature-prediction-based data center robot inspection system, a temperature-prediction-based data center robot, electronic equipment, and a computer-readable storage medium, which possess all the advantages of the aforementioned temperature-prediction-based data center robot inspection method. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram of the first process of the computer room robot inspection method based on temperature prediction in this application.

[0041] Figure 2This is a schematic diagram of the second process of the computer room robot inspection method based on temperature prediction in this application;

[0042] Figure 3 This is a connection diagram of a computer room robot inspection system based on temperature prediction, as described in this application.

[0043] Figure 4 This is another connection diagram of the computer room robot inspection system based on temperature prediction in this application;

[0044] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0045] Figure 6 This is a schematic diagram of another structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0048] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0049] In the description of the embodiments of this application, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. In addition, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0050] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0051] In the description of the embodiments of this application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0052] Data centers are used to store, process, and manage large amounts of data, and typically include servers, storage devices, and network equipment. Data centers can provide various data services, such as data storage, backup and recovery, data encryption, and security. Data centers often require efficient power and cooling systems, highly reliable network and security systems, and intelligent monitoring and management systems. With the continuous development of the digital age, the demand for data centers is constantly increasing.

[0053] In data center server rooms, server racks are used to house critical information technology equipment such as servers, network devices, and storage devices. Server racks are not merely simple tools for equipment storage and management; they also offer rich functionality and scalability. Air conditioning systems are also an essential facility in data centers. Servers and other IT equipment in data centers generate a significant amount of heat; therefore, air conditioning systems are needed to provide stable power supply and cooling for the IT equipment, ensuring its reliability and stability. Servers are one of the core pieces of equipment in a data center. Servers are critical devices used for storing and processing data, providing efficient, secure, and reliable data storage and processing services for various applications. The performance and reliability of servers directly impact the performance and reliability of the entire data center.

[0054] Data centers typically employ data center robots, primarily for tasks such as inspection, equipment testing, and environmental monitoring. Given the enormous annual power consumption of data centers and the fact that rack operating temperatures often exceed permissible reliability limits, monitoring rack operating temperatures is crucial. Robotic inspection not only offers the flexibility and intelligence of manual inspection but also avoids potential omissions, misreadings, and misrecordings, reducing labor costs and improving inspection quality and efficiency. However, existing data center robotic inspection systems still suffer from technical limitations, including the inability to predict faults in advance and relatively low inspection efficiency.

[0055] To address the aforementioned issues, this application proposes a data center robot based on temperature prediction, an inspection method, and related devices. The following detailed description of this application is provided in conjunction with embodiments and accompanying drawings.

[0056] like Figure 1 The diagram shown is a first flowchart of the data center robot inspection method based on temperature prediction according to this application, which may include:

[0057] S101, obtain temperature-related parameter data for the computer room.

[0058] In practical applications, the specific temperature-related parameters of the computer room can be determined according to the actual prediction requirements. For example, they may include the computer room temperature, the external ambient temperature, the load of equipment in the rack, the configuration and operation status of the air conditioning system, and the humidity of the computer room. This application does not impose specific restrictions.

[0059] S102, input the temperature correlation parameter data into the rack temperature prediction model to obtain the temperature prediction results of each rack in the computer room.

[0060] It should be noted that the rack temperature prediction model is a mathematical model used to predict the temperature of data center racks. In practical applications, rack temperature prediction models can employ various algorithms and techniques, such as linear regression models, neural network models, and support vector machine models.

[0061] The input to the rack temperature prediction model can be temperature-related parameter data of the data center, and the output is the temperature prediction result for each rack. In practical applications, a training set can be formed using a large amount of temperature-related parameter data of the data center and the temperature conditions of the racks. The rack temperature prediction model can be trained using the training set to enable it to be used for prediction.

[0062] S103, based on the temperature prediction results of each cabinet, the cabinets are divided into high-temperature warning state, low-temperature warning state, and normal state. Specifically, the predicted temperature of the cabinets in the high-temperature warning state is higher than a preset high-temperature threshold, the predicted temperature of the cabinets in the low-temperature warning state is lower than a preset low-temperature threshold, and the predicted temperature of the cabinets in the normal state is between the preset high-temperature threshold and the preset low-temperature threshold.

[0063] In practical applications, the preset high-temperature threshold and preset low-temperature threshold can be set according to the safe operation requirements of the cabinet, and this application does not impose any restrictions. All cabinets are classified according to temperature prediction results to facilitate the application of different inspection strategies for different categories of cabinets.

[0064] S104 enables the data center robot to inspect cabinets under high temperature warning status from high to low according to the temperature prediction results, inspect cabinets under low temperature warning status from low to high according to the temperature prediction results, and inspect cabinets under normal status according to the shortest path.

[0065] In practical applications, inspections can be conducted first, prioritizing racks based on the severity of high-temperature warnings, and then secondly, prioritizing racks based on the severity of low-temperature warnings. The time taken by the inspection robot to inspect racks in normal conditions is assessed, and the robot is controlled to inspect the remaining racks using the shortest path. Therefore, the inspection path and sequence of the data center robot can be adjusted in real-time based on the current temperature prediction results for each rack.

[0066] This application offers the advantage of real-time performance. The rack temperature prediction model can predict temperatures in real time based on data related to the server room's temperature parameters, enabling the server room robot to obtain the latest temperature prediction results promptly. This allows the robot to quickly respond to temperature anomalies and take appropriate inspection measures, effectively reducing the impact of temperature anomalies on equipment. Secondly, based on the temperature prediction results from the rack temperature prediction model, the server room robot can automatically adjust its inspection route and priority. According to the predicted temperature status, the robot can selectively inspect racks under high-temperature or low-temperature warning conditions, improving inspection efficiency and accuracy. Finally, this application offers cost advantages. By predicting rack temperatures, the server room robot can help detect temperature anomalies in advance, avoiding damage and malfunctions caused by overheating or overcooling of equipment. This helps reduce the cost of repairing and replacing equipment and extends its service life.

[0067] like Figure 2 The diagram shown is a schematic representation of the second process of the computer room robot inspection method based on temperature prediction in this application, which may include:

[0068] S201 collects data on the number of servers in the data center, rack power consumption, external ambient temperature, internal temperature, and air conditioning equipment power, performs statistical analysis, and uses this data as temperature-related parameters for the data center.

[0069] In practical applications, the internal temperature of the computer room can be measured using parameters such as the temperature of the air conditioning equipment and the temperature of the server.

[0070] S202 uses the K-means clustering algorithm to preprocess the collected temperature-related parameter data of the computer room to obtain preprocessed data.

[0071] Preprocessing with the K-means clustering algorithm can reduce overall data redundancy. When multiple features are highly correlated and describe the same attribute or relationship, the information provided by these features is redundant. The K-means clustering algorithm can iteratively divide the points in the dataset into K clusters, making the data points in the same cluster as similar as possible. In this way, originally highly correlated data points will be grouped into the same cluster, thereby reducing data redundancy. The K-means clustering algorithm may include the following steps:

[0072] The original data set X containing n objects is divided into K clusters such that the distance from each data point to the cluster center is minimized. This completes the cluster analysis and reduces overall redundancy. Initialize the K cluster centers:

[0073]

[0074] in, This represents the first cluster center initialized. This represents the second cluster center after initialization. This represents the k-th cluster center during initialization.

[0075] Assigning n data points to the cluster set with the minimum squared Euclidean distance to their cluster centers completes the "nearest neighbor cluster center" classification. The classification principle is:

[0076]

[0077] in, x represents the cluster belonging to the i-th cluster in the t-th iteration; p Represents clustered objects; Let j represent the j-th cluster center in the t-th iteration; j represents the number of cluster centers.

[0078] The computing nodes are assigned new sample centers from the cluster set, that is:

[0079]

[0080] in, Let x represent the new sample centers of the j-th cluster set in the t-th iteration. j This represents the j-th cluster object in the cluster set.

[0081] The two steps above are repeated iteratively until the cluster centers no longer change, or a certain number of iterations are reached. Determining the number of clusters k can be difficult when dealing with large amounts of experimental data. The Elbow method from the k-value evaluation algorithm is used to determine this number, with the optimization objective being:

[0082]

[0083] Where, c (i) For x (i) The index of the nearest cluster center, μ k Let J be the cluster center. The optimization objective J is the sum of the distances from each sample to the cluster center, which also represents the clustering error. The smaller the J value, the smaller the clustering error and the better the clustering effect. The K-means algorithm is used to cluster the initial samples, the J cost function is used to evaluate the clustering effect, and the Elbow algorithm is used to determine the optimal K value.

[0084] S203, standardize the preprocessed data.

[0085] To avoid variables becoming overly dependent on their specific unit properties and variation ranges, clustered data is standardized to further improve dataset quality, which is beneficial for subsequent modeling, training, and data analysis. The preprocessed data can be further processed by assigning equal weights to each cluster and mapping each cluster to the same variation range. This ensures that data in each category varies within the same scale and range and is mapped to the same variation range, thereby improving data consistency and comparability.

[0086] S204. Construct a rack temperature prediction model. The rack temperature prediction model uses a BP neural network optimized by a genetic algorithm and is trained.

[0087] Backpropagation (BP) neural networks, also known as backpropagation neural networks, are a training algorithm based on multilayer feedforward neural networks and are one of the most widely used network models in the field of neural networks. BP neural networks have high structural reliability and excellent predictive capabilities, but they also have some drawbacks, such as slow convergence speed and susceptibility to getting trapped in local optima. BP neural networks are a model similar to the structure of the human brain, possessing powerful data processing and adaptive capabilities. Through training, they can effectively establish a mapping relationship between input and output, solving various nonlinear problems.

[0088] A backpropagation (BP) neural network optimized using a genetic algorithm can improve the accuracy of the prediction model by optimizing the initial threshold and weights. MATLAB's built-in GA toolbox can be used to optimize the initial population's threshold and weights using a genetic algorithm. Applying a genetic algorithm to optimize a BP neural network effectively overcomes its tendency to get trapped in local minima, quickly and accurately finding the optimal BP neural network solution.

[0089] In practical applications, other solutions can also be used to replace the BP neural network, for example:

[0090] (1) Support Vector Machine (SVM): Support Vector Machine is a supervised learning algorithm that can be used for regression and classification problems. It performs well in handling small sample data and nonlinear data and is suitable for temperature prediction tasks.

[0091] (2) Random Forest: Random forest is an ensemble learning algorithm that can be used for regression and classification problems. It can handle large-scale datasets, is robust to feature selection, and can handle high-dimensional data, so it can also be used for temperature prediction.

[0092] (3) Long Short-Term Memory Network (LSTM): LSTM is a recurrent neural network suitable for predicting sequential data. For time-dependent temperature data, LSTM can effectively capture patterns in the sequence and make predictions.

[0093] (4) Convolutional Neural Network (CNN): Convolutional neural networks are commonly used for processing image and visual data, but in some cases they can also be used for temperature prediction, especially when temperature data can be represented as a two-dimensional or multi-dimensional matrix.

[0094] (5) Genetic Algorithm: The genetic algorithm is an optimization algorithm that can be used for parameter optimization and model selection. It can combine different prediction models and find the best temperature prediction model through an evolutionary process.

[0095] You can choose according to your needs.

[0096] S205 inputs temperature-related parameter data into the rack temperature prediction model to obtain the temperature prediction results for each rack in the computer room.

[0097] When building a rack temperature prediction model, the influence of objective factors should be considered. In order to accurately and effectively reflect the temperature prediction results of the data center environment, based on the BP neural network model theory, five parameters can be selected to build a neural network algorithm model, namely power consumption w1, internal temperature t1, external temperature t2, air conditioning power w2, and number of servers n.

[0098] A backpropagation (BP) neural network model typically consists of an input layer, hidden layers, and an output layer connected sequentially. Following the 2N+1 rule (where N represents the number of nodes in the input layer), we can set the number of hidden layer nodes to 11 and the output layer to 1. For example, the prediction function for the server rack temperature T in a computer room can be expressed as:

[0099] T = f(w1, t1, t2, w2, n).

[0100] S206. Based on the temperature prediction results of the server racks, server racks in the computer room whose temperature prediction results are higher than the preset high temperature threshold are classified as high temperature warning states, server racks in the computer room whose temperature prediction results are lower than the preset low temperature threshold are classified as low temperature warning states, and server racks in the computer room whose temperature prediction results are between the preset low temperature threshold and the preset high temperature threshold are classified as normal states.

[0101] S207, the data center robot adjusts its inspection route in real time based on the status of each server rack and reports the inspection results.

[0102] First, the racks can be inspected according to the severity of their high-temperature warnings, from most severe to least severe. Second, the data center robot can inspect racks according to the severity of their low-temperature warnings, from most severe to least severe. Finally, the time required for inspecting racks under normal conditions can be estimated, and the data center robot can be controlled to inspect the remaining racks using the shortest path.

[0103] In this way, the data center robot can adjust in real time according to the predicted temperature status of the server rack and conduct inspections in an orderly manner according to the severity of the warning status, so as to improve the efficiency and pertinence of the inspection.

[0104] This application utilizes an improved BP neural network to enhance the accuracy of temperature prediction by learning from and training on large amounts of data. Compared to traditional methods, the data center robot can more accurately determine the temperature status of server racks, reducing the possibility of misjudgments and omissions, and offering the advantage of high accuracy. Furthermore, the BP neural network model optimized based on a genetic algorithm in this application can more quickly and accurately locate server racks with abnormal temperatures, reducing the workload and time required for manual inspections and improving work efficiency and resource utilization.

[0105] like Figure 3 As shown, based on the above-mentioned temperature prediction-based data center robot inspection method, this application also proposes a temperature prediction-based data center robot inspection system, which may include:

[0106] The data acquisition module is used to acquire temperature-related parameter data for the computer room.

[0107] The prediction module is used to input temperature-related parameter data into the rack temperature prediction model to obtain the temperature prediction results of each rack in the computer room.

[0108] The classification module is used to classify the cabinets into high temperature warning state, low temperature warning state and normal state according to the temperature prediction results of each cabinet. The temperature prediction result of the cabinet in the high temperature warning state is higher than the preset high temperature threshold, the temperature prediction result of the cabinet in the low temperature warning state is lower than the preset low temperature threshold, and the temperature prediction result of the cabinet in the normal state is between the preset high temperature threshold and the preset low temperature threshold.

[0109] The control module enables the data center robot to inspect cabinets under high temperature warning from high to low according to the temperature prediction results, cabinets under low temperature warning from low to high according to the temperature prediction results, and cabinets under normal conditions to inspect according to the shortest path.

[0110] like Figure 4 As shown, in some embodiments of the computer room robot inspection system based on temperature prediction in this application, a preprocessing module and a standardization module may also be included. The preprocessing module is used to preprocess the temperature-related parameter data of the computer room using a K-means clustering algorithm to obtain preprocessed data. The standardization module is used to standardize the preprocessed data.

[0111] In some embodiments of the data center robot inspection system based on temperature prediction in this application, a building module may also be included for building a cabinet temperature prediction model.

[0112] In addition to the aforementioned temperature-prediction-based computer room robot inspection method, this application also proposes a temperature-prediction-based computer room robot, including a robot body and a control unit for controlling the movement of the robot body. The control unit stores a computer program, which, when executed by a processor, implements the steps of the aforementioned temperature-prediction-based computer room robot inspection method.

[0113] It should be noted that, in the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another device, or some features may be ignored or not executed. The modules described as separate components may or may not be physically separated. The components shown as modules may be one or more physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0114] Furthermore, the modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0115] like Figure 5As shown in the embodiment of this application, an electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the temperature prediction-based computer room robot inspection method described in any of the above embodiments.

[0116] like Figure 6 As shown in the embodiments of this application, another electronic device may further include: an input port connected to a processor for transmitting multimodal data collected by an external acquisition device to the processor; a display unit connected to the processor for displaying the processor's processing results to the outside world; and a communication module connected to the processor for enabling communication between the electronic device and the outside world. The display unit may be a display panel, a laser scanner, or the like; the communication method used by the communication module includes, but is not limited to, Mobile High Definition Link (HML), Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), wireless connectivity: Wireless Fidelity (WiFi), Bluetooth communication technology, Bluetooth Low Energy communication technology, and IEEE 802.11s-based communication technology.

[0117] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the temperature prediction-based computer room robot inspection method described in any of the above embodiments.

[0118] The computer-readable storage media involved in this application include random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage media known in the art.

[0119] For descriptions of relevant parts of the temperature-prediction-based data center robot inspection system, electronic equipment, and computer-readable storage medium provided in this application's embodiments, please refer to the detailed descriptions of the corresponding parts in the temperature-prediction-based data center robot inspection method provided in this application's embodiments; they will not be repeated here. Furthermore, parts of the technical solutions provided in this application that are consistent with the implementation principles of corresponding technical solutions in the prior art have not been described in detail to avoid excessive elaboration.

[0120] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for robot-assisted inspection of a computer room based on temperature prediction, characterized in that, include: Obtain temperature-related parameter data for the computer room; The K-means clustering algorithm is used to preprocess the temperature-related parameter data of the computer room to obtain preprocessed data. The data of each category after clustering the preprocessed data are assigned the same weight, and the data of each category are mapped to the same variation range. Input the temperature correlation parameter data into the rack temperature prediction model to obtain the temperature prediction results of each rack in the computer room; Based on the temperature prediction results of each cabinet, the cabinets are divided into high temperature warning state, low temperature warning state, and normal state. The temperature prediction result of the cabinet in the high temperature warning state is higher than the preset high temperature threshold, the temperature prediction result of the cabinet in the low temperature warning state is lower than the preset low temperature threshold, and the temperature prediction result of the cabinet in the normal state is between the preset high temperature threshold and the preset low temperature threshold. The data center robot inspects cabinets under high temperature warning from high to low according to the temperature prediction results, cabinets under low temperature warning from low to high according to the temperature prediction results, and cabinets under normal conditions are inspected using the shortest path.

2. The computer room robot inspection method based on temperature prediction according to claim 1, characterized in that, The cabinet temperature prediction model includes: A BP neural network model optimized using a genetic algorithm.

3. The computer room robot inspection method based on temperature prediction according to claim 2, characterized in that, Also includes: Using the threshold and weights of the initial population of the BP neural network model as the optimization objects, the genetic algorithm is used through the GA toolbox of MATLAB to optimize the cabinet temperature prediction model.

4. The computer room robot inspection method based on temperature prediction according to claim 3, characterized in that, The BP neural network model includes: The input layer, hidden layer, and output layer are connected in sequence, with the output layer having 1 node and the hidden layer having 2N+1 nodes; where N is the number of nodes in the input layer.

5. The computer room robot inspection method based on temperature prediction according to claim 4, characterized in that, The temperature-related parameter data of the computer room includes: the number of servers in the computer room, the power consumption of the server racks, the external ambient temperature of the computer room, the internal temperature of the computer room, and the power of the air conditioning equipment in the computer room.

6. A temperature-prediction-based robotic inspection system for computer rooms, used to implement the temperature-prediction-based robotic inspection method for computer rooms as described in any one of claims 1 to 5, characterized in that, include: The data acquisition module is used to acquire temperature-related parameter data for the computer room. The prediction module is used to input temperature-related parameter data into the rack temperature prediction model to obtain the temperature prediction results of each rack in the computer room. The classification module is used to classify the cabinets into high temperature warning state, low temperature warning state and normal state according to the temperature prediction results of each cabinet. The temperature prediction result of the cabinet in the high temperature warning state is higher than the preset high temperature threshold, the temperature prediction result of the cabinet in the low temperature warning state is lower than the preset low temperature threshold, and the temperature prediction result of the cabinet in the normal state is between the preset high temperature threshold and the preset low temperature threshold. The control module enables the data center robot to inspect cabinets under high temperature warning from high to low according to the temperature prediction results, cabinets under low temperature warning from low to high according to the temperature prediction results, and cabinets under normal conditions to inspect according to the shortest path.

7. The computer room robot inspection system based on temperature prediction according to claim 6, characterized in that, Also includes: Preprocessing module and standardization module; The preprocessing module is used to preprocess the temperature-related parameter data of the computer room using the K-means clustering algorithm to obtain preprocessed data; The standardization processing module is used to standardize the preprocessed data.

8. A computer room robot based on temperature prediction, comprising a robot body and a control unit for controlling the movement of the robot body; characterized in that, The control unit stores a computer program, which, when executed by a processor, implements the steps of the temperature prediction-based computer room robot inspection method as described in any one of claims 1 to 5.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the temperature prediction-based computer room robot inspection method as described in any one of claims 1 to 5 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the temperature prediction-based computer room robot inspection method as described in any one of claims 1 to 5.

Images