Intelligent environment monitoring system for server cabinet

Abstract

The invention, which relates to the technical field of intelligent monitoring, discloses a server cabinet intelligent environment monitoring system comprising a central management system which is in communication connection with a server cabinet data acquisition module, an energy optimization and remote access alarm module and a dynamic adjustment and remote monitoring module. The server cabinet data acquisition module is integrated with a door magnetic switch, a thermal imaging camera and an intelligent electric meter through an Alicloud IoT suite to realize door state monitoring, temperature visualization and power consumption measurement of the server cabinet; the energy optimization and remote access alarm module constructs an LSTM model, predicts power consumption and temperature trend, and constructs a centralized management interface by means of an AP I gateway and security service; the dynamic adjustment and remote monitoring module dynamically adjusts a cooling and power supply strategy according to an actual load; the central management system summarizes and analyzes data and coordinates operation of all the modules. The whole scheme aims at optimizing energy use and improving the operation efficiency of the data center.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring, and in particular to an intelligent environment monitoring system for a server cabinet. Background Art

[0002] With the rapid development of information technology, the scale of various information infrastructures such as data centers and cloud computing centers has continued to expand, and the requirements for the operating environment of server cabinets have become increasingly higher. Traditional environmental monitoring methods can no longer meet the needs of modern data centers for efficiency, stability, and security. The server cabinet intelligent environment monitoring system realizes comprehensive, real-time, and intelligent monitoring of the internal environment of the cabinet by integrating sensor networks, data analysis, remote monitoring and other technologies. The system can monitor key parameters such as temperature, humidity, and air quality in the cabinet in real time, and alarm and warn according to preset thresholds, effectively preventing equipment failures and data loss caused by environmental factors. Looking to the future, with the continuous integration and innovation of technologies such as the Internet of Things, big data, and artificial intelligence, the server cabinet intelligent environment monitoring system will be more intelligent and automated, providing more efficient and reliable monitoring and management services for data centers. This will not only further enhance the security and stability of data centers, but also promote the continuous progress and innovative development of information technology.

[0003] The intelligent environment monitoring system of server cabinets plays a key role in improving the efficiency and security of data center operation and maintenance, but it still needs to continue to improve in remote access and alarm, and energy use optimization. To achieve this goal, the system uses deep integrated monitoring technology to implement comprehensive monitoring of power supply status, air flow speed and direction, and physical intrusion. In terms of power management, the system can track the power usage of each device and even the entire cabinet group in real time, and provide managers with detailed energy consumption analysis reports to help precise regulation and reduce energy waste. At the same time, by monitoring the air flow speed and direction, the system can evaluate the efficiency of the cooling system, ensure that hot air is effectively discharged and cold air is evenly distributed, which not only improves the operating stability of the server, but also further optimizes the energy use efficiency. In terms of security, the system can quickly identify and respond to any unauthorized access attempts by recording the opening / closing time of the cabinet door and combining it with intelligent analysis algorithms, thus building a solid physical security barrier for the data center. More importantly, all these monitoring and management operations can be achieved through remote access. Once an abnormality is detected, the system will immediately trigger the alarm mechanism to notify relevant personnel to take prompt action, thereby greatly reducing operation and maintenance costs and improving response speed. In summary, through continuous technological innovation and optimization, the server cabinet intelligent environment monitoring system is gradually overcoming challenges in remote access and alarm, energy usage optimization, etc., providing strong support for the efficient, safe and sustainable operation of data centers. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a server cabinet intelligent environment monitoring system, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a server cabinet intelligent environment monitoring system, including a central management system, the central management system is communicatively connected with a server cabinet data acquisition module, an energy optimization and remote access alarm module and a dynamic adjustment and remote monitoring module;

[0006] The server cabinet data collection module includes a door magnetic switch, a thermal imaging camera, and a smart meter connected to the Alibaba Cloud IoT suite, which records the opening and closing time of the server cabinet door, generates a visual temperature distribution map, and measures the power consumption of the server cabinet;

[0007] The energy optimization and remote access alarm module uses the Alibaba Cloud PAI platform to train the LSTM model, dynamically adjusts the cooling system and power distribution strategy according to the actual load, and performs remote access and real-time monitoring;

[0008] The dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load conditions and the prediction results of the LSTM model, and performs remote access and alarm through the centralized management interface;

[0009] The central management system aggregates and analyzes collected data, coordinates the work of each module, and provides a centralized management interface for operation and maintenance personnel to remotely access and monitor system status in real time.

[0010] Furthermore, the process of the server cabinet data acquisition module recording the opening and closing time of the server cabinet door through the door magnetic switch includes:

[0011] The door magnetic switch generates an electrical signal by detecting the opening and closing status of the server cabinet door. The signal is converted into digital information by the server cabinet data acquisition module and uploaded to the central management system through the Internet of Things protocol. The central management system receives and records the time of each status change of the server cabinet door, and triggers the alarm mechanism according to the preset rules. The operation and maintenance personnel can view the status and historical records of the server cabinet door in real time through the management interface. When the server cabinet door is opened during non-working hours, the system automatically sends a notification to the designated personnel.

[0012] Furthermore, the process of the server cabinet data acquisition module generating a visual temperature distribution map through a thermal imaging camera includes:

[0013] Thermal imaging cameras capture infrared radiation inside the cabinet to generate temperature distribution maps;

[0014] The image data of the temperature distribution map is processed by the server cabinet data acquisition module and transmitted to the central management system via the network. The central management system analyzes the temperature distribution map and identifies hot spots;

[0015] The preset alarm threshold is compared with the hot spot. If it reaches or exceeds the alarm threshold, the alarm is triggered. The operation and maintenance personnel can quickly locate the heat source by viewing the thermal image in real time, and then take measures for cooling and maintenance.

[0016] Furthermore, the process of the server cabinet data acquisition module measuring the power consumption of the server cabinet through the smart meter includes:

[0017] Smart meters monitor the voltage and current parameters of server cabinets in real time and calculate power consumption using built-in algorithms;

[0018] For DC circuits, instantaneous power P1 = V × I, where P1 represents power, V represents voltage, and I represents current. For AC circuits, the power factor PF is integrated to calculate active power. The formula is P2 = V × I × PF, where P2 is active power and PF is power factor.

[0019] The accumulated electric energy consumption is further calculated by integrating the power value within a fixed time period. The calculation result is transmitted to the server cabinet data acquisition module through the built-in wireless network. The data is forwarded to the central management system for analysis and processing, and the power consumption trend is recorded and displayed. The alarm is triggered according to the preset power consumption threshold to remind the operation and maintenance personnel to pay attention to abnormal energy consumption.

[0020] Furthermore, the process of training the LSTM model input layer using the Alibaba Cloud PAI platform in the energy optimization and remote access alarm module includes:

[0021] Create a new project on the Alibaba Cloud PAI platform, select a deep learning framework, and build an LSTM-based server cabinet energy optimization model. The LSTM model includes an input layer, a hidden layer, a fully connected layer, and an output layer. The LSTM model input layer cleans the collected raw data, converts the numerical data to the same scale, and arranges the data in chronological order to form continuous time series data. The temperature information of key areas is extracted from the temperature distribution map and the power consumption trend is extracted from the power consumption data as the input features of the LSTM model. The key areas include the CPU, GPU, power module, disk area, vents, and fans in the server cabinet.

[0022] Furthermore, the process of training the hidden layer of the LSTM model using the Alibaba Cloud PAI platform in the energy optimization and remote access alarm module includes:

[0023] The hidden layer of the LSTM model consists of a forget gate, an input gate, a cell state, and an output gate. The forget gate is used to decide whether to discard the memory state C of the previous moment. t-1 The calculation process of the content in the middle is as follows:

[0024] f t =σ(W f ·[h t-1 , x t ]+b f )

[0025] Among them, f t is the output of the forget gate, indicating the proportion of information to be retained, W f is the weight matrix of the forget gate, h t-1 is the hidden state at the previous moment, x t is the input vector at the current moment, b f is the bias term of the forget gate, σ is the sigmoid activation function, which produces a value between 0 and 1 and is used to control the state update of the memory unit;

[0026] The input gate is used to convert the candidate new cell state C t1 Added to the memory unit, the calculation process is as follows:

[0027] i t =σ(W i ·[h t-1 , x t ]+b i )

[0028] Among them, i t is the output of the input gate, indicating the updated information ratio, W i is the weight matrix of the input gate, b i is the bias term of the input gate,

[0029] C t1 =tanh(W C ·[h t-1 , x t ]+b C )

[0030] Among them, C t1 is a candidate new cell state, W C is the weight matrix for generating candidate cell states, b C is the bias term for generating candidate cell states, tanh is the hyperbolic tangent activation function, which produces values ​​between -1 and 1;

[0031] The cell state is responsible for storing long-term memory and its calculation process is as follows:

[0032] C t =ft ·C t-1 +i t ·C t1

[0033] Among them, C t is the updated cell state, C t-1 is the cell state at the previous moment, f t ·C t-1 Represents the old state part controlled by the forget gate, i t ·C t1 The new state part representing the input gate control;

[0034] The output gate controls the information in the memory unit that is output to the next hidden layer and the output layer. The calculation process is as follows:

[0035] o t =σ(W o ·[h t-1 , x t ]+b o )

[0036] Among them, t is the output of the output gate, indicating the proportion of information to be output, W o is the weight matrix of the output gate, b o is the bias term of the output gate,

[0037] h t =o t tanh(C t )

[0038] Among them, h t is the hidden state at the current moment, tanh(C t ) is the cell state after tanh activation.

[0039] Furthermore, the energy optimization and remote access alarm module uses the Alibaba Cloud PAI platform to train the LSTM model's fully connected layer and output layer, and the process of dynamically adjusting the cooling system and power distribution strategy according to the actual load includes:

[0040] The fully connected layer of the LSTM model maps the output of the hidden layer. The calculation process is as follows:

[0041] y t =W y ·h t +b y

[0042] Among them, y t is the output of the fully connected layer, W y is the weight matrix of the fully connected layer, b yis the bias term of the fully connected layer, h t is the hidden state output of the LSTM layer;

[0043] The output layer of the LSTM model predicts temperature changes based on the server cabinet energy optimization model, automatically adjusts the air-conditioning temperature, and optimizes the power distribution between different cabinets according to the load prediction results.

[0044] Furthermore, the energy optimization and remote access alarm module builds a centralized management interface based on the API gateway and security authentication service provided by Alibaba Cloud. The process of realizing remote access and real-time monitoring includes:

[0045] The server cabinet door status change information detected by the door magnetic switch is uploaded to the central management system through the Alibaba Cloud IoT suite. The API gateway, as a key component, is responsible for receiving requests from the web and forwarding them to the backend service for processing. It also provides flow control and authentication functions. By using the JWT security token mechanism, different permissions are assigned to users with different roles, allowing administrators to view the status of all cabinet doors in real time through the Web interface, and immediately receive alarm notifications when unauthorized personnel access the server cabinet door or open it during non-working hours, and take corresponding measures.

[0046] Furthermore, the dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load conditions and the prediction results of the LSTM model, and the process of remote access and alarm through the centralized management interface includes:

[0047] The LSTM model trained on the Alibaba Cloud PAI platform identifies load change patterns by learning historical data and predicts load conditions accordingly. When the forecast shows a trend toward high load, the dynamic adjustment and remote monitoring module pre-adjusts the air conditioning settings. For power distribution, the system optimizes power supply based on the predicted load demand and executes adjustment measures through the centralized management interface. Administrators can view current operating parameters, historical data trends, and LSTM model prediction results through the centralized management interface.

[0048] The alarm function of the centralized management interface is used to generate alarms for detected anomalies, including temperature exceeding the safe range, abnormal energy consumption, unauthorized access, and server cabinet doors being opened during non-working hours.

[0049] Furthermore, the central management system aggregates and analyzes the collected data, coordinates the work of each module, and provides a centralized management interface for operation and maintenance personnel to remotely access and monitor the system status in real time, including:

[0050] In the server cabinet intelligent environment monitoring system, the central management system first receives all information from the server cabinet data acquisition module, including the door magnetic switch status, the temperature distribution map generated by the thermal imaging camera, and the power consumption data recorded by the smart meter. The real-time data is used for instant status monitoring and deep learning is performed through the LSTM model to predict the load conditions. Based on the actual load and the prediction results of the LSTM model, the central management system automatically adjusts the air conditioning settings and power distribution strategies. The central management system uses the API gateway and security authentication services provided by Alibaba Cloud to build a centralized management interface. Operation and maintenance personnel remotely access the system through the centralized management interface to view the current operating status, historical data trends, and forecast information. When the system detects any abnormal situation, it immediately triggers the alarm mechanism to notify relevant personnel to take measures.

[0051] The present invention provides a server cabinet intelligent environment monitoring system, which has the following beneficial effects:

[0052] The server cabinet intelligent environment monitoring system provides a comprehensive and efficient management solution for data centers by integrating advanced IoT technology and machine learning algorithms. First, the server cabinet data acquisition module uses the door magnetic switch, thermal imaging camera, and smart meter connected by the Alibaba Cloud IoT suite to not only record the opening and closing status of the cabinet door, but also generate a visual temperature distribution map and accurately measure power consumption, which helps operation and maintenance personnel to detect abnormal conditions in a timely manner and take preventive measures to avoid potential failures. Secondly, the energy optimization and remote access alarm module dynamically adjusts the cooling system and power distribution strategy according to the actual load based on the LSTM model trained on the Alibaba Cloud PAI platform, improves the energy efficiency ratio, reduces unnecessary power consumption, and ensures that the server runs in the best working environment, extending the hardware life. In addition, the module also builds a centralized management interface, allowing the operation and maintenance team to easily access and monitor remotely and in real time, greatly improving work efficiency. Finally, the server cabinet dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load and prediction results, further enhancing the system's adaptive ability. When an abnormality occurs, the system can immediately trigger the alarm mechanism to notify relevant personnel to respond quickly. The central management system is the core, responsible for aggregating all data, analyzing and processing, and coordinating the collaboration between various functional modules, providing a unified operating platform, simplifying daily maintenance processes, and improving fault diagnosis speed and processing efficiency. In summary, this system significantly enhances the security, reliability, and energy efficiency of the data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A block diagram of a server cabinet intelligent environment monitoring system according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, the present invention provides a technical solution: a server cabinet intelligent environment monitoring system, including a central management system, the central management system is communicatively connected with a server cabinet data acquisition module, an energy optimization and remote access alarm module and a dynamic adjustment and remote monitoring module;

[0056] The server cabinet data collection module includes a door magnetic switch, thermal imaging camera, and smart meter connected to the Alibaba Cloud IoT suite to record the opening and closing time of the server cabinet door, generate a visual temperature distribution map, and measure the power consumption of the server cabinet;

[0057] The energy optimization and remote access alarm module uses the Alibaba Cloud PAI platform to train the LSTM model, dynamically adjust the cooling system and power distribution strategy according to the actual load, and conduct remote access and real-time monitoring.

[0058] The dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load conditions and the prediction results of the LSTM model, and performs remote access and alarms through the centralized management interface;

[0059] The central management system aggregates and analyzes collected data, coordinates the work of each module, and provides a centralized management interface for operation and maintenance personnel to remotely access and monitor system status in real time.

[0060] The process of the server cabinet data acquisition module recording the opening and closing time of the server cabinet door through the door magnetic switch includes:

[0061] The door magnetic switch generates an electrical signal by detecting the opening and closing status of the server cabinet door. The signal is converted into digital information by the server cabinet data acquisition module and uploaded to the central management system through the Internet of Things protocol. The central management system receives and records the time of each status change of the server cabinet door, and triggers the alarm mechanism according to the preset rules. The operation and maintenance personnel can view the status and historical records of the server cabinet door in real time through the management interface. When the server cabinet door is opened during non-working hours, the system automatically sends a notification to the designated personnel.

[0062] The process by which the server cabinet data acquisition module generates a visual temperature distribution map through a thermal imaging camera includes:

[0063] Thermal imaging cameras capture infrared radiation inside the cabinet to generate temperature distribution maps;

[0064] The image data of the temperature distribution map is processed by the server cabinet data acquisition module and transmitted to the central management system via the network. The central management system analyzes the temperature distribution map and identifies hot spots;

[0065] The preset alarm threshold is compared with the hot spot. If it reaches or exceeds the alarm threshold, the alarm is triggered. The operation and maintenance personnel can quickly locate the heat source by viewing the thermal image in real time, and then take measures for cooling and maintenance.

[0066] The process of the server cabinet data acquisition module measuring the power consumption of the server cabinet through the smart meter includes:

[0067] Smart meters monitor the voltage and current parameters of server cabinets in real time and calculate power consumption using built-in algorithms;

[0068] For DC circuits, instantaneous power P1 = V × I, where P1 represents power, V represents voltage, and I represents current. For AC circuits, the power factor PF is integrated to calculate active power. The formula is P2 = V × I × PF, where P2 is active power and PF is power factor.

[0069] The accumulated electric energy consumption is further calculated by integrating the power value within a fixed time period. The calculation result is transmitted to the server cabinet data acquisition module through the built-in wireless network. The data is forwarded to the central management system for analysis and processing, and the power consumption trend is recorded and displayed. The alarm is triggered according to the preset power consumption threshold to remind the operation and maintenance personnel to pay attention to abnormal energy consumption.

[0070] The process of using Alibaba Cloud PAI platform to train the input layer of the LSTM model for the energy optimization and remote access alarm module includes:

[0071] Create a new project on the Alibaba Cloud PAI platform, select the deep learning framework, and build an LSTM-based server cabinet energy optimization model. The LSTM model includes an input layer, a hidden layer, a fully connected layer, and an output layer. The LSTM model input layer cleans the collected raw data, converts the numerical data to the same scale, and arranges the data in chronological order to form continuous time series data. The temperature information of key areas is extracted from the temperature distribution map and the power consumption trend is extracted from the power consumption data as the input features of the LSTM model. The key areas include the CPU, GPU, power module, disk area, vents, and fans in the server cabinet.

[0072] The process of training the hidden layer of the LSTM model using the Alibaba Cloud PAI platform for the energy optimization and remote access alarm module includes:

[0073] The hidden layer of the LSTM model consists of a forget gate, an input gate, a cell state, and an output gate. The forget gate is used to decide whether to discard the memory state C of the previous moment. t-1 The calculation process of the content in the middle is as follows:

[0074] f t =σ(W f ·[h t-1 , x t ]+b f )

[0075] Among them, f t is the output of the forget gate, indicating the proportion of information to be retained, W f is the weight matrix of the forget gate, h t-1 is the hidden state at the previous moment, x t is the input vector at the current moment, b f is the bias term of the forget gate, σ is the sigmoid activation function, which produces a value between 0 and 1 and is used to control the state update of the memory unit;

[0076] The input gate is used to convert the candidate new cell state C t1 Added to the memory unit, the calculation process is as follows:

[0077] i t =σ(W i ·[h t-1 , x t ]+b i )

[0078] Among them, i t is the output of the input gate, indicating the updated information ratio, W i is the weight matrix of the input gate, b i is the bias term of the input gate,

[0079] C t1 =tanh(W C ·[h t-1 , x t ]+b C )

[0080] Among them, C t1 is a candidate new cell state, W C is the weight matrix for generating candidate cell states, b C is the bias term for generating candidate cell states, tanh is the hyperbolic tangent activation function, which produces values ​​between -1 and 1;

[0081] The cell state is responsible for storing long-term memory and its calculation process is as follows:

[0082] C t =ft ·C t-1 +i t ·C t1

[0083] Among them, C t is the updated cell state, C t-1 is the cell state at the previous moment, f t ·C t-1 Represents the old state part controlled by the forget gate, i t ·C t1 The new state part representing the input gate control;

[0084] The output gate controls the information in the memory unit that is output to the next hidden layer and the output layer. The calculation process is as follows:

[0085] ot=σ(W o ·[h t-1 , x t ]+b o )

[0086] Among them, t is the output of the output gate, indicating the proportion of information to be output, W o is the weight matrix of the output gate, b o is the bias term of the output gate,

[0087] h t =o t tanh(C t )

[0088] Among them, h t is the hidden state at the current moment, tanh(C t ) is the cell state after tanh activation.

[0089] The energy optimization and remote access alarm module uses the Alibaba Cloud PAI platform to train the LSTM model's fully connected layer and output layer. The process of dynamically adjusting the cooling system and power distribution strategy based on the actual load includes:

[0090] The fully connected layer of the LSTM model maps the output of the hidden layer. The calculation process is as follows:

[0091] y t =W y ·h t +b y

[0092] Among them, y t is the output of the fully connected layer, W y is the weight matrix of the fully connected layer, b y is the bias term of the fully connected layer, h tis the hidden state output of the LSTM layer;

[0093] The output layer of the LSTM model predicts temperature changes based on the server cabinet energy optimization model, automatically adjusts the air-conditioning temperature, and optimizes the power distribution between different cabinets according to the load prediction results.

[0094] The energy optimization and remote access alarm module builds a centralized management interface based on the API gateway and security authentication services provided by Alibaba Cloud. The process of implementing remote access and real-time monitoring includes:

[0095] The server cabinet door status change information detected by the door magnetic switch is uploaded to the central management system through the Alibaba Cloud IoT suite. The API gateway, as a key component, is responsible for receiving requests from the web and forwarding them to the backend service for processing. It also provides flow control and authentication functions. By using the JWT security token mechanism, different permissions are assigned to users with different roles, allowing administrators to view the status of all cabinet doors in real time through the Web interface, and immediately receive alarm notifications when unauthorized personnel access the server cabinet door or open it during non-working hours, and take corresponding measures.

[0096] The dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load conditions and the prediction results of the LSTM model. The process of remote access and alarm through the centralized management interface includes:

[0097] The LSTM model trained on the Alibaba Cloud PAI platform identifies load change patterns by learning historical data and predicts load conditions accordingly. When the forecast shows a trend toward high load, the dynamic adjustment and remote monitoring module pre-adjusts the air conditioning settings. For power distribution, the system optimizes power supply based on the predicted load demand and executes adjustment measures through the centralized management interface. Administrators can view current operating parameters, historical data trends, and LSTM model prediction results through the centralized management interface.

[0098] Utilize the alarm function of the centralized management interface to generate alarms for detected anomalies, including temperature exceeding the safe range, abnormal energy consumption, unauthorized access, and server cabinet doors being opened during non-working hours.

[0099] The central management system aggregates and analyzes collected data, coordinates the work of each module, and provides a centralized management interface for operation and maintenance personnel to remotely access and monitor the system status in real time. The process includes:

[0100] In the server cabinet intelligent environment monitoring system, the central management system first receives all information from the server cabinet data acquisition module, including the door magnetic switch status, the temperature distribution map generated by the thermal imaging camera, and the power consumption data recorded by the smart meter. The real-time data is used for instant status monitoring and deep learning is performed through the LSTM model to predict the load conditions. Based on the actual load and the prediction results of the LSTM model, the central management system automatically adjusts the air conditioning settings and power distribution strategies. The central management system uses the API gateway and security authentication services provided by Alibaba Cloud to build a centralized management interface. Operation and maintenance personnel remotely access the system through the centralized management interface to view the current operating status, historical data trends, and forecast information. When the system detects any abnormal situation, it immediately triggers the alarm mechanism to notify relevant personnel to take measures.

[0101] The server cabinet intelligent environment monitoring system first connects the door magnetic switch, thermal imaging camera, and smart meter to the server cabinet data acquisition module through the Alibaba Cloud IoT suite to ensure that all devices are correctly connected and can work properly. After startup, the system automatically records the opening and closing time of the server cabinet door, generates a temperature distribution map, and measures the power consumption. This information is transmitted to the central management system in real time for summary analysis. The LSTM model is trained using the Alibaba Cloud PAI platform to predict future cooling needs and power distribution based on actual load. Based on the prediction results, the system automatically adjusts the working status of the cooling system and the power supply strategy to achieve the best energy efficiency ratio. A centralized management interface is built through the API gateway and security authentication services provided by Alibaba Cloud, allowing operation and maintenance personnel to securely access the system from anywhere, view the current status, and receive alarm notifications from the system. As more data accumulates, the LSTM model continues to learn and improve its prediction accuracy. At the same time, the operation and maintenance team makes corresponding adjustments to the physical facilities based on the information fed back by the system to further improve the overall performance of the data center. When an abnormal situation is detected, the system immediately issues an alarm and notifies relevant personnel to take measures in a pre-set manner to prevent potential problems from worsening. In summary, this solution is designed to provide a data center with an efficient, energy-saving and easy-to-manage operating environment, which greatly simplifies daily operation and maintenance processes while also enhancing security.

[0102] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions. The sentence "includes an element defined by ... does not exclude the existence of other identical elements in the process, method, article or device including the element".

[0103] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A server cabinet intelligent environment monitoring system, characterized in that: It includes a central management system, which is communicatively connected to a server cabinet data acquisition module, an energy optimization and remote access alarm module, and a dynamic adjustment and remote monitoring module; The server cabinet data acquisition module includes a door magnetic switch, a thermal imaging camera, and a smart meter connected to the Alibaba Cloud IoT kit, which records the opening and closing time of the server cabinet door, generates a visual temperature distribution map, and measures the power consumption of the server cabinet; The energy optimization and remote access alarm module uses the Alibaba Cloud PAI platform to train the LSTM model, dynamically adjusts the cooling system and power distribution strategy according to the actual load, and performs remote access and real-time monitoring; The dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load conditions and the prediction results of the LSTM model, and performs remote access and alarm through the centralized management interface; The central management system aggregates and analyzes collected data, coordinates the work of each module, and provides a centralized management interface for operation and maintenance personnel to remotely access and monitor system status in real time.

2. The server cabinet intelligent environment monitoring system according to claim 1, characterized in that: The process of the server cabinet data acquisition module recording the opening and closing time of the server cabinet door through the door magnetic switch includes: The door magnetic switch generates an electrical signal by detecting the opening and closing status of the server cabinet door. The signal is converted into digital information by the server cabinet data acquisition module and uploaded to the central management system through the Internet of Things protocol; The central management system receives and records the time of each server cabinet door status change, and triggers the alarm mechanism according to preset rules; Operation and maintenance personnel can view the status and history of server cabinet doors in real time through the management interface. When the server cabinet door is opened during non-working hours, the system automatically sends a notification to the designated personnel.

3. The server cabinet intelligent environment monitoring system according to claim 2, characterized in that: The process of the server cabinet data acquisition module generating a visual temperature distribution map through a thermal imaging camera includes: Capture the infrared radiation inside the cabinet through a thermal imaging camera to generate a temperature distribution map; After the image data of the temperature distribution map is processed by the server cabinet data acquisition module, it is transmitted to the central management system via the network. The central management system analyzes the temperature distribution map and identifies hot spots; The preset alarm threshold is compared with the hot spot. If it reaches or exceeds the alarm threshold, the alarm is triggered. The operation and maintenance personnel can locate the heat source by viewing the thermal image in real time and take measures for cooling and maintenance.

4. The server cabinet intelligent environment monitoring system according to claim 3, characterized in that: The process of the server cabinet data acquisition module measuring the power consumption of the server cabinet through the smart meter includes: Smart meters monitor the voltage and current parameters of server cabinets in real time and calculate power consumption using built-in algorithms; For DC circuits, instantaneous power P1 = V × I, where P1 represents power, V represents voltage, and I represents current. For AC circuits, the power factor PF is integrated to calculate active power. The formula is P2 = V × I × PF, where P2 is active power and PF is power factor. The accumulated electric energy consumption is further calculated by integrating the power value within a fixed time period. The calculation result is transmitted to the server cabinet data acquisition module through the built-in wireless network. The data is forwarded to the central management system for analysis and processing, and the power consumption trend is recorded and displayed. The alarm is triggered according to the preset power consumption threshold to remind the operation and maintenance personnel to pay attention to abnormal energy consumption.

5. The server cabinet intelligent environment monitoring system according to claim 4, characterized in that: The process of using the Alibaba Cloud PAI platform to train the LSTM model input layer in the energy optimization and remote access alarm module includes: Create a new project on the Alibaba Cloud PAI platform, select a deep learning framework, and build an LSTM-based server cabinet energy optimization model. The LSTM model includes an input layer, a hidden layer, a fully connected layer, and an output layer. The LSTM model input layer cleans the collected raw data, converts the numerical data to the same scale, arranges them in chronological order, forms continuous time series data, and extracts temperature information of key areas from the temperature distribution map and power consumption trends from the power consumption data as input features of the LSTM model. The key areas include the CPU, GPU, power module, disk area, vents, and fans in the server cabinet.

6. The server cabinet intelligent environment monitoring system according to claim 5, characterized in that: The process of using the Alibaba Cloud PAI platform to train the hidden layer of the LSTM model in the energy optimization and remote access alarm module includes: The hidden layer of the LSTM model consists of a forget gate, an input gate, a cell state, and an output gate. The forget gate is used to decide whether to discard the memory state C of the previous moment. t-1 The calculation process of the content in the middle is as follows: f t =σ(W f ·[h t-1 ,x t ]+b f ) Among them, f t is the output of the forget gate, indicating the proportion of information to be retained, W f is the weight matrix of the forget gate, h t-1 is the hidden state at the previous moment, x t is the input vector at the current moment, b f is the bias term of the forget gate, σ is the sigmoid activation function, which produces a value between 0 and 1 and is used to control the state update of the memory unit; The input gate is used to convert the candidate new cell state C t1 Added to the memory unit, the calculation process is as follows: i t =σ(W i ·[h t-1 ,x t ]+b i ) Among them, i t is the output of the input gate, indicating the updated information ratio, W i is the weight matrix of the input gate, b i is the bias term of the input gate; C t1 =tanh(W C ·[h t-1 ,x t ]+b C ) Among them, C t1 is a candidate new cell state, W C is the weight matrix for generating candidate cell states, b C is the bias term for generating candidate cell states, tanh is the hyperbolic tangent activation function, which produces values ​​between -1 and 1; The cell state is responsible for storing long-term memory and its calculation process is as follows: C t =f t ·C t-1 +i t ·C t1 Among them, C t is the updated cell state, C t-1 is the cell state at the previous moment, f t ·C t-1 Represents the old state part controlled by the forget gate, i t ·C t1 The new state part representing the input gate control; The output gate controls the information in the memory unit that is output to the next hidden layer and the output layer. The calculation process is as follows: the t =σ(W o ·[h t-1 ,x t ]+b o ) Among them, t is the output of the output gate, indicating the proportion of information to be output, W o is the weight matrix of the output gate, b o is the bias term of the output gate; h t =o t ·tanh(C t ) Among them, h t is the hidden state at the current moment, tanh(C t ) is the cell state after tanh activation.

7. The server cabinet intelligent environment monitoring system according to claim 6, characterized in that: The energy optimization and remote access alarm module uses the Alibaba Cloud PAI platform to train the LSTM model's fully connected layer and output layer. The process of dynamically adjusting the cooling system and power distribution strategy according to the actual load includes: The fully connected layer of the LSTM model maps the output of the hidden layer. The calculation process is as follows: y t =W y ·h t +b y Among them, y t is the output of the fully connected layer, W y is the weight matrix of the fully connected layer, b y is the bias term of the fully connected layer, h t is the hidden state output of the LSTM layer; The output layer of the LSTM model predicts temperature changes based on the server cabinet energy optimization model, automatically adjusts the air-conditioning temperature, and optimizes the power distribution between different cabinets according to the load prediction results.

8. The server cabinet intelligent environment monitoring system according to claim 7, characterized in that: The energy optimization and remote access alarm module builds a centralized management interface based on the API gateway and security authentication service provided by Alibaba Cloud. The process of realizing remote access and real-time monitoring includes: The server cabinet door status change information detected by the door magnetic switch is uploaded to the central management system through the Alibaba Cloud IoT suite. The API gateway receives requests from the web and forwards them to the backend service for processing. It configures flow control and authentication functions. By using the JWT security token mechanism, different permissions are assigned to users with different roles, allowing administrators to view the status of all cabinet doors in real time through the Web interface. When the server cabinet door is accessed by unauthorized personnel or opened during non-working hours, they will immediately receive an alarm notification and take corresponding measures.

9. The server cabinet intelligent environment monitoring system according to claim 8, characterized in that: The dynamic adjustment and remote monitoring module automatically adjusts the cooling system and power distribution strategy according to the actual load conditions and the prediction results of the LSTM model, and the process of remote access and alarm through the centralized management interface includes: The LSTM model trained on the Alibaba Cloud PAI platform identifies load change patterns by learning historical data and predicts load conditions accordingly. When the forecast shows a trend toward high load, the dynamic adjustment and remote monitoring module pre-adjusts the air conditioning settings. For power distribution, the system optimizes power supply based on the predicted load demand and executes adjustment measures through the centralized management interface. Administrators can view current operating parameters, historical data trends, and LSTM model prediction results through the centralized management interface. The alarm function of the centralized management interface is used to generate alarms for detected anomalies, including temperature exceeding the safe range, abnormal energy consumption, unauthorized access, and server cabinet doors being opened during non-working hours.

10. The server cabinet intelligent environment monitoring system according to claim 9, characterized in that: The central management system aggregates and analyzes the collected data, coordinates the work of each module, and provides a centralized management interface for operation and maintenance personnel to remotely access and monitor the system status in real time. The process includes: In the server cabinet intelligent environment monitoring system, the central management system first receives all information from the server cabinet data acquisition module, including the door magnetic switch status, the temperature distribution map generated by the thermal imaging camera, and the power consumption data recorded by the smart meter. The real-time data is used for instant status monitoring; Through deep learning of LSTM model, load conditions are predicted. Based on the actual load and the prediction results of LSTM model, the central management system automatically adjusts the air conditioning settings and power distribution strategy; The central management system uses the API gateway and security authentication service provided by Alibaba Cloud to build a centralized management interface. Operation and maintenance personnel can remotely access the system through the centralized management interface to view the current operating status, historical data trends, and forecast information. When the system detects any abnormal situation, it immediately triggers the alarm mechanism to notify relevant personnel to take measures.

Images