Server room safety monitoring system and method

Abstract

The invention discloses a server room safety monitoring system and method, and relates to the technical field of safety monitoring, and the method comprises the steps: collecting environment data and electric power parameter data in a server room through a sensor, and carrying out the preprocessing; constructing a deep learning model based on a multi-modal fusion neural network, and carrying out joint learning and analysis on the environment data and the power parameter data; an environment adjusting strategy is made according to the abnormal condition and the environment data, a generated environment adjusting instruction is sent to corresponding equipment, and the equipment executes adjusting operation and feeds back running state information to the monitoring system. The environment and power condition of the machine room can be comprehensively and deeply monitored, the system can intelligently adjust environment parameters according to the actual requirements of the machine room, the precision and efficiency of environment control are improved, errors and hysteresis caused by manual adjustment are reduced, meanwhile, the energy consumption of the machine room is optimized, and the energy consumption of the machine room is reduced. Unnecessary energy waste is avoided, and the operation cost of a machine room is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of security monitoring, and in particular to a server room security monitoring system and method. Background Art

[0002] In recent years, with the rapid development of information technology, the scale of data centers and server rooms has continued to expand, and the number and density of their internal equipment has increased. As a core place that carries a large number of key information systems and business applications, server rooms have extremely high requirements for their security and stability. In traditional server room management, the monitoring of environmental data and power parameter data often adopts a relatively scattered and simple method. In terms of environmental data monitoring, usually only temperature sensors and humidity sensors are set separately, and data collection only stays at the basic level. There is a lack of comprehensive consideration of multi-dimensional environmental data and the ability to deeply analyze their interrelationships. In terms of power parameter monitoring, it focuses on real-time measurement of basic parameters such as current and voltage. There is insufficient research on the complex correlation between power parameters and the potential interactive effects between the power system and the environmental system. Once a power failure or abnormal fluctuation occurs, traditional monitoring methods are difficult to quickly evaluate its impact on the entire room environment and services. The comprehensive impact on the operation of server equipment is likely to cause the expansion of the fault scope or long-term server downtime, bringing huge economic losses and business interruption risks to enterprises and users. Traditional monitoring systems lack intelligent data analysis and decision-making capabilities. Data processing mostly relies on manual experience judgment or simple threshold comparison. It cannot automatically adapt to the dynamic changes in the operation status of the computer room. It is difficult to mine valuable information from massive data to warn of potential safety hazards in advance. When dealing with abnormal situations, there is a lack of effective collaborative linkage mechanism between the systems. Environmental adjustment equipment, server equipment, and power supply equipment cannot achieve intelligent interaction and cooperation, resulting in low problem solving efficiency and unable to meet the urgent needs of modern server rooms for high reliability, high availability and intelligent management. Traditional monitoring and management methods are difficult to achieve refined management and optimal utilization of computer room energy, and cannot effectively reduce energy consumption and improve the overall energy efficiency of the computer room while ensuring the normal operation of the server.

[0003] However, the current common solutions have many shortcomings, including: the existing technology lacks the ability to jointly learn and deeply analyze environmental data and power parameter data, and is unable to explore the potential correlation and mutual influence between the two. Changes in ambient temperature will affect the conversion efficiency of the server power supply, which is then reflected in the fluctuation of power parameters, but traditional technology is difficult to detect this subtle correlation and cannot take preventive measures before a failure occurs. Existing technology cannot automatically generate accurate environmental adjustment instructions based on abnormal conditions and environmental data, and usually requires manual intervention for complex analysis and decision-making, which not only consumes a lot of time, but also easily leads to improper problem handling due to human errors. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above problems existing in the existing server room security monitoring system and method, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a server room security monitoring system and method, which is suitable for solving the problem that the existing technology lacks the ability to jointly learn and deeply analyze environmental data and power parameter data, and is unable to explore the potential correlation and mutual influence between the two. Changes in ambient temperature will affect the conversion efficiency of the server power supply, which is then reflected in the fluctuation of power parameters, but traditional technology is difficult to detect this subtle correlation and cannot take preventive measures before a failure occurs.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In the first aspect, an embodiment of the present invention provides a server room security monitoring method, which includes using sensors to collect environmental data and power parameter data in the server room and preprocessing them; building a deep learning model based on a multimodal fusion neural network and jointly learning and analyzing the environmental data and power parameter data; when it is determined to be an abnormal situation, immediately triggering an alarm mechanism and further analyzing the relationship between the abnormal type and the environmental data; formulating an environmental adjustment strategy based on the abnormal situation and environmental data, and sending the generated environmental adjustment instructions to the corresponding equipment, the equipment executes the adjustment operation and feeds back the operating status information to the monitoring system.

[0009] As a preferred solution of the server room security monitoring method described in the present invention, wherein: the environmental data includes temperature data, humidity data, air quality data and air flow data; the power parameter data includes current data, voltage data, power data and power factor data; the alarm mechanism includes sound and light alarm, message notification alarm, monitoring center alarm display and remote alarm interface; the abnormality types include equipment failure-related abnormalities, environmental abnormalities and safety-related abnormalities; the equipment includes temperature control equipment, humidity control equipment and air quality control equipment; the adjustment operation includes temperature adjustment operation, humidity adjustment operation and air quality adjustment operation.

[0010] As a preferred solution of the server room security monitoring method described in the present invention, the specific steps of constructing the deep learning model are as follows: using sensors to obtain environmental data and power parameter data in the server room and preprocessing them; constructing a deep learning model based on a multimodal fusion neural network; using a machine learning algorithm to jointly learn and analyze environmental data and power parameter data; when the monitoring system determines that it is an abnormal situation, the monitoring system immediately triggers an alarm mechanism and further analyzes the relationship between the abnormal type and the environmental data; formulates an environmental adjustment strategy based on the abnormal situation and environmental data; sends the generated environmental adjustment instructions to the corresponding equipment; the equipment executes the adjustment operation and feeds back the operating status information to the monitoring system.

[0011] As a preferred solution of the server room security monitoring method of the present invention, the specific formula for calculating the comprehensive value of the environmental data is as follows:

[0012]

[0013] Among them, E is the comprehensive value of environmental data; T is temperature data; H is humidity data; Q is air quality data; F is air flow data;

[0014] The specific formula for calculating the comprehensive power value is as follows:

[0015]

[0016] Among them, K is the comprehensive value of power data; I is the current data; V is the voltage data; W is the power data; PF is the power factor data;

[0017] The specific formula for joint learning and analysis of the environmental data and power parameter data is as follows:

[0018]

[0019] Among them, F is the fusion value of environmental data and power parameter data; E is the comprehensive value of environmental data; K is the comprehensive value of power data.

[0020] As a preferred solution of the server room security monitoring method of the present invention, the specific formula for determining abnormal conditions is as follows:

[0021]

[0022] Among them, P is the abnormal judgment result; F is the fusion value of environmental data and power parameter data; t is the abnormal judgment threshold.

[0023] As a preferred solution of the server room security monitoring method described in the present invention, the specific situation of the abnormal judgment result is as follows: when the fusion value F of the environmental data and the power parameter data is less than or equal to the abnormal judgment threshold t, the value of the abnormal judgment result P is 0, which means that the computer room is judged to be in normal condition based on the currently collected temperature, humidity, air quality, air flow, current, voltage, power and power factor data; when the fusion value F of the environmental data and the power parameter data is greater than the abnormal judgment threshold t, the value of the abnormal judgment result P is 1, which means that the computer room is judged to be in abnormal condition based on the currently collected temperature, humidity, air quality, air flow, current, voltage, power and power factor data, and an alarm or environmental adjustment operation is triggered at this time.

[0024] As a preferred solution of the server room security monitoring method described in the present invention, the specific steps of formulating the environmental adjustment strategy are as follows: collecting environmental data, power parameter data and historical normal operating data under the current abnormal state; further analyzing the relationship between the abnormal type and the environmental data according to the judgment result of the abnormal situation by the deep learning algorithm model, and clarifying the type of the current abnormality; setting the environmental adjustment target for the current abnormal situation based on the standard operating environment requirements of the server room and the equipment operating parameter range; formulating a specific environmental adjustment strategy according to the abnormal type and the adjustment target; generating detailed environmental adjustment instructions from the environmental adjustment strategy; sending the instructions to the corresponding device according to the communication protocol and interface requirements of the device; after the device executes the adjustment operation, receiving the operating status information fed back by the device.

[0025] In the second aspect, in order to further solve the above-mentioned technical problems, the embodiments of the present invention provide a server room security monitoring system, which includes: a data collection module, which is used to collect and pre-process environmental data and power parameter data in the server room; a model building module, which is used to build a deep learning model and jointly learn and analyze environmental data and power parameter data; an exception handling module, which is used to immediately trigger an alarm mechanism when an abnormal situation is determined and further analyze the relationship between the abnormal type and the environmental data; an adjustment feedback module, which is used to formulate an environmental adjustment strategy according to the abnormal situation and environmental data, and send the environmental adjustment instruction to the corresponding equipment, and the equipment executes the adjustment operation and feeds back the operating status information to the monitoring system.

[0026] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of a server room security monitoring method as described in the first aspect of the present invention is implemented.

[0027] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of a server room security monitoring method as described in the first aspect of the present invention is implemented.

[0028] The beneficial effects of the present invention are as follows: the present invention combines multimodal data acquisition with deep learning analysis, and can conduct comprehensive and in-depth monitoring of the environment and power conditions of the computer room. Automatically formulating and executing environmental adjustment strategies based on abnormal conditions and environmental data is a highlight of the present invention. The system can intelligently adjust environmental parameters according to the actual needs of the computer room. When the temperature is too high, it automatically adjusts the cooling power, ventilation direction and air volume of the air conditioner to ensure that the server is in a suitable temperature environment; when the humidity is abnormal, it accurately controls the operation of the humidifier or dehumidifier to maintain a suitable humidity level to ensure the normal operation and life of the equipment. This automated adjustment mechanism not only improves the accuracy and efficiency of environmental control, but also reduces the errors and lags that may be caused by manual adjustment. At the same time, it optimizes the energy consumption of the computer room, avoids unnecessary energy waste, and reduces the operating costs of the computer room, which is in line with the development concept of modern green data centers. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0030] Figure 1 This is a flow chart for implementing the present invention in Example 1.

[0031] Figure 2 This is a dynamic adjustment diagram of the environmental regulation strategy in Example 1. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0035] Example 1

[0036] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a server room security monitoring method, comprising the following steps:

[0037] S1: Use sensors to collect environmental data and power parameter data in the server room and perform preprocessing.

[0038] Preferably, Figure 1 The figure shows the implementation process of the present invention. First, sensors are used to collect environmental data and power parameter data in the server room and preprocess them. Then, a deep learning model is constructed based on a multimodal fusion neural network, and the environmental data and power parameter data are jointly learned and analyzed. When an abnormal situation is determined, an alarm mechanism is immediately triggered and the relationship between the abnormal type and the environmental data is further analyzed. Finally, an environmental adjustment strategy is formulated based on the abnormal situation and environmental data, and the generated environmental adjustment instructions are sent to the corresponding equipment. The equipment executes the adjustment operation and feeds back the operating status information to the monitoring system.

[0039] Furthermore, the environmental data includes temperature data, humidity data, air quality data, and air flow data.

[0040] Furthermore, the power parameter data includes current data, voltage data, power data and power factor data.

[0041] Specifically, preprocessing ensures the quality and consistency of data by performing real-time preprocessing of environmental data and power parameter data on data nodes, including data cleaning, noise reduction, and standardization.

[0042] S2: Build a deep learning model based on a multimodal fusion neural network and jointly learn and analyze environmental data and power parameter data.

[0043] Preferably, the specific steps of constructing the deep learning model are as follows: using sensors to obtain environmental data and power parameter data in the server room and perform preprocessing.

[0044] Build a deep learning model based on multimodal fusion neural network.

[0045] Use machine learning algorithms to jointly learn and analyze environmental data and power parameter data.

[0046] When the monitoring system determines that an abnormal situation occurs, the monitoring system immediately triggers the alarm mechanism and further analyzes the relationship between the abnormal type and the environmental data.

[0047] Develop environmental adjustment strategies based on abnormal conditions and environmental data.

[0048] The generated environment adjustment instructions are sent to the corresponding devices.

[0049] The equipment performs regulation operations and feeds back operating status information to the monitoring system.

[0050] Furthermore, the specific formula for calculating the comprehensive value of environmental data is as follows:

[0051]

[0052] Among them, E is the comprehensive value of environmental data; T is temperature data; H is humidity data; Q is air quality data; and F is air flow data.

[0053] The specific formula for calculating the comprehensive value of electricity is as follows:

[0054]

[0055] Among them, K is the comprehensive value of power data; I is the current data; V is the voltage data; W is the power data; PF is the power factor data.

[0056] The specific formula for joint learning and analysis of environmental data and power parameter data is as follows:

[0057]

[0058] Among them, F is the fusion value of environmental data and power parameter data; E is the comprehensive value of environmental data; K is the comprehensive value of power data.

[0059] Furthermore, the specific formula for determining abnormal situations is as follows:

[0060]

[0061] Among them, P is the abnormal judgment result; F is the fusion value of environmental data and power parameter data; t is the abnormal judgment threshold.

[0062] Furthermore, the anomaly determination threshold is determined based on the statistical analysis of historical data of the server room, the recommendations and standards of the equipment manufacturer, experimental and simulation tests, and risk assessment and business demand orientation.

[0063] Specifically, the specific situation of the abnormal judgment result is as follows: when the fusion value F of the environmental data and the power parameter data is less than or equal to the abnormal judgment threshold t, and the value of the abnormal judgment result P is 0, it means that based on the currently collected temperature, humidity, air quality, air flow, current, voltage, power and power factor data, it is judged that the computer room is in normal condition.

[0064] When the fusion value F of environmental data and power parameter data is greater than the abnormal judgment threshold t, and the value of the abnormal judgment result P is 1, it means that based on the currently collected temperature, humidity, air quality, air flow, current, voltage, power and power factor data, the computer room is judged to be in an abnormal condition, and an alarm or environmental adjustment operation is triggered.

[0065] S3: When an abnormal situation is determined, the alarm mechanism is immediately triggered and the relationship between the abnormal type and the environmental data is further analyzed.

[0066] Furthermore, the alarm mechanism includes sound and light alarm, message notification alarm, monitoring center alarm display and remote alarm interface.

[0067] Furthermore, the exception types include equipment failure related exceptions, environmental exceptions, and safety related exceptions.

[0068] Preferably, further analysis of the relationship between the abnormal type and environmental data can accurately locate the root cause of the fault. Compared with traditional general abnormal alarms and blind troubleshooting, it greatly shortens the fault repair time and reduces operation and maintenance costs.

[0069] S4: Formulate environmental adjustment strategies based on abnormal conditions and environmental data, and send the generated environmental adjustment instructions to the corresponding devices. The devices execute the adjustment operations and feed back the operating status information to the monitoring system.

[0070] Furthermore, the equipment includes temperature regulating equipment, humidity regulating equipment and air quality regulating equipment.

[0071] Furthermore, the adjustment operation includes a temperature adjustment operation, a humidity adjustment operation and an air quality adjustment operation.

[0072] Specifically, the steps for formulating an environmental adjustment strategy are as follows: Collect environmental data, power parameter data under the current abnormal state, and historical normal operation data.

[0073] Based on the judgment results of the deep learning algorithm model on abnormal situations, the relationship between the abnormal type and the environmental data is further analyzed to clarify the type of the current abnormality.

[0074] Based on the standard operating environment requirements of the server room and the equipment operating parameter range, set environmental adjustment targets for current abnormal situations.

[0075] Develop specific environmental adjustment strategies based on the abnormality type and adjustment objectives.

[0076] Generate detailed environmental adjustment instructions from environmental adjustment strategies.

[0077] Send the instructions to the corresponding device according to the communication protocol and interface requirements of the device.

[0078] After the device performs the adjustment operation, the operating status information fed back by the device is received.

[0079] Preferably, the environmental adjustment strategy formulated based on abnormal conditions and environmental data is targeted and dynamically adaptable. For different abnormal types and environmental conditions, appropriate adjustment instructions are automatically generated and sent to the corresponding equipment. After the equipment performs the adjustment operation, it feeds back the operating status information. The system can adjust the strategy in real time according to the feedback to form a closed-loop control.

[0080] Preferably, compared with traditional or fixed-mode environmental adjustments, this intelligent control mechanism can more accurately maintain the stability of the computer room environment, reduce damage to the server due to environmental fluctuations, extend the service life of the equipment, optimize energy consumption, and improve the overall energy efficiency of the computer room.

[0081] This embodiment also provides a server room security monitoring system, including: a data collection module, used to collect environmental data and power parameter data in the server room and perform preprocessing; a model construction module, used to build a deep learning model and jointly learn and analyze environmental data and power parameter data; an exception handling module, used to immediately trigger an alarm mechanism when an abnormal situation is determined and further analyze the relationship between the abnormal type and the environmental data; an adjustment feedback module, used to formulate an environmental adjustment strategy based on the abnormal situation and environmental data, and send the environmental adjustment instruction to the corresponding equipment, the equipment executes the adjustment operation and feeds back the operating status information to the monitoring system.

[0082] This embodiment also provides a computer device, which is applicable to a server room security monitoring method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a server room security monitoring method proposed in the above embodiment.

[0083] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0084] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a server room security monitoring method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0085] In summary, the present invention combines multimodal data acquisition with deep learning analysis, which can conduct comprehensive and in-depth monitoring of the environment and power conditions of the computer room. Automatically formulating and executing environmental adjustment strategies based on abnormal conditions and environmental data is a highlight of the present invention. The system can intelligently adjust environmental parameters according to the actual needs of the computer room. When the temperature is too high, it automatically adjusts the cooling power, ventilation direction and air volume of the air conditioner to ensure that the server is in a suitable temperature environment; when the humidity is abnormal, it accurately controls the operation of the humidifier or dehumidifier to maintain a suitable humidity level to ensure the normal operation and life of the equipment. This automated adjustment mechanism not only improves the accuracy and efficiency of environmental control, but also reduces the errors and lags that may be caused by manual adjustment. At the same time, it optimizes the energy consumption of the computer room, avoids unnecessary energy waste, and reduces the operating costs of the computer room, which is in line with the development concept of modern green data centers.

[0086] Example 2

[0087] Referring to Tables 1 and 2, the second embodiment of the present invention is shown. This embodiment is different from the first embodiment in that, in order to verify its beneficial effects, operating data and related instructions of the present invention in an actual environment are provided.

[0088] As shown in Table 1 and Table 2, the comparison between the traditional technology and the technology of the present invention in the core data of server room security monitoring and the comprehensive performance evaluation of server room security monitoring in this example is shown.

[0089] Table 1 Comparison of core data of server room security monitoring

[0090]

[0091] Table 2 Comprehensive performance evaluation table of server room security monitoring

[0092]

[0093] As can be seen from the above table, the present invention can conduct comprehensive and in-depth monitoring of the environment and power conditions in the service area computer room, and can intelligently adjust environmental parameters according to the actual needs of the computer room, thereby improving the accuracy and efficiency of environmental control and reducing the errors and lags that may be caused by manual adjustment.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A server room security monitoring method, characterized in that: include: Use sensors to collect and pre-process environmental data and power parameter data in the server room; Build a deep learning model based on multimodal fusion neural network and conduct joint learning and analysis of environmental data and power parameter data; When an abnormal situation is determined, the alarm mechanism is triggered immediately and the relationship between the abnormal type and environmental data is further analyzed; Formulate environmental adjustment strategies based on abnormal conditions and environmental data, and send the generated environmental adjustment instructions to the corresponding equipment. The equipment executes the adjustment operation and feeds back the operating status information to the monitoring system.

2. The server room security monitoring method according to claim 1, characterized in that: The environmental data includes temperature data, humidity data, air quality data and air flow data; The power parameter data includes current data, voltage data, power data and power factor data; The alarm mechanism includes sound and light alarm, message notification alarm, monitoring center alarm display and remote alarm interface; The abnormality types include equipment failure related abnormalities, environmental abnormalities and safety related abnormalities; The equipment includes temperature control equipment, humidity control equipment and air quality control equipment; The adjustment operation includes a temperature adjustment operation, a humidity adjustment operation and an air quality adjustment operation.

3. The server room security monitoring method according to claim 2, characterized in that: The specific steps of building a deep learning model are as follows: Use sensors to obtain environmental data and power parameter data in the server room and pre-process them; Build a deep learning model based on multimodal fusion neural network; Use machine learning algorithms to jointly learn and analyze environmental data and power parameter data; When the monitoring system determines an abnormal situation, it immediately triggers the alarm mechanism and further analyzes the relationship between the abnormal type and environmental data; Develop environmental adjustment strategies based on abnormal conditions and environmental data; Sending the generated environment adjustment instructions to the corresponding devices; The equipment performs regulation operations and feeds back operating status information to the monitoring system.

4. The server room security monitoring method according to claim 3, characterized in that: The specific formula for calculating the comprehensive value of environmental data is as follows: Among them, E is the comprehensive value of environmental data; T is temperature data; H is humidity data; Q is air quality data; F is air flow data; The specific formula for calculating the comprehensive power value is as follows: Among them, K is the comprehensive value of power data; I is the current data; V is the voltage data; W is the power data; PF is the power factor data; The specific formula for joint learning and analysis of the environmental data and power parameter data is as follows: Among them, F is the fusion value of environmental data and power parameter data; E is the comprehensive value of environmental data; K is the comprehensive value of power data.

5. The server room security monitoring method according to claim 4, characterized in that: The specific formula for determining abnormal situations is as follows: Among them, P is the abnormal judgment result; F is the fusion value of environmental data and power parameter data; t is the abnormal judgment threshold.

6. The server room security monitoring method according to claim 5, characterized in that: The specific situation of the abnormal determination result is as follows: When the fusion value F of the environmental data and the power parameter data is less than or equal to the abnormality determination threshold t, and the value of the abnormality determination result P is 0, it means that the computer room is judged to be in normal condition based on the currently collected temperature, humidity, air quality, air flow, current, voltage, power and power factor data; When the fusion value F of environmental data and power parameter data is greater than the abnormal judgment threshold t, and the value of the abnormal judgment result P is 1, it means that based on the currently collected temperature, humidity, air quality, air flow, current, voltage, power and power factor data, the computer room is judged to be in an abnormal condition, and an alarm or environmental adjustment operation is triggered.

7. The server room security monitoring method according to claim 6, characterized in that: The specific steps of formulating the environmental adjustment strategy are as follows: Collect environmental data, power parameter data and historical normal operation data under current abnormal conditions; Based on the abnormal situation judgment results of the deep learning algorithm model, the relationship between the abnormal type and the environmental data is further analyzed to clarify the type of the current abnormality; Based on the standard operating environment requirements of the server room and the equipment operating parameter range, set environmental adjustment targets for current abnormal situations; Formulate specific environmental adjustment strategies based on the abnormality type and adjustment target; Generate detailed environmental adjustment instructions from environmental adjustment strategies; Send the command to the corresponding device according to the communication protocol and interface requirements of the device; After the device performs the adjustment operation, the operating status information fed back by the device is received.

8. A server room security monitoring system, based on a server room security monitoring method according to any one of claims 1 to 7, characterized in that: include, A data collection module is used to collect and pre-process environmental data and power parameter data in the server room; A model building module, which is used to build a deep learning model and jointly learn and analyze environmental data and power parameter data; The exception handling module is used to immediately trigger the alarm mechanism when an abnormal situation is determined and further analyze the relationship between the abnormal type and environmental data; The adjustment feedback module is used to formulate environmental adjustment strategies based on abnormal conditions and environmental data, and send environmental adjustment instructions to corresponding devices. The devices execute adjustment operations and feedback operating status information to the monitoring system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a server room security monitoring method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a server room security monitoring method described in any one of claims 1 to 7 are implemented.

Images