Machine room power environment monitoring system based on sine cosine algorithm optimization processing

Abstract

The application provides a machine room power environment monitoring system based on sine-cosine algorithm optimization processing, which comprises a data acquisition module, a processing module, an alarm module, an execution module and a communication module; the system method collects and transmits various power parameters and environmental parameters in the machine room through the data acquisition module, processes and analyzes the collected data by using the optimization algorithm of the sine-cosine algorithm of the processing module, judges whether there is an abnormal condition in the machine room, sends an alarm signal in time when an abnormal condition is found by the alarm module, meanwhile, the execution module executes corresponding control operation according to the instruction sent by the processing module, and the communication module transmits the monitoring data and the alarm information to the remote monitoring center and the mobile device of the maintenance personnel to process the abnormal parameters in time, realizes real-time monitoring of various power equipment and environmental parameters in the machine room, realizes intelligent alarm and automatic control, and improves the safety and stability of the operation of the machine room.

Description

Technical Field

[0001] This invention relates to the field of data center management and power environment monitoring technology, specifically a data center power environment monitoring system based on sine and cosine algorithm optimization. Background Technology

[0002] In recent years, the rapid development of information technology and the economy has led to an increasing demand for data centers, servers, and computer rooms. As an important location for data processing and equipment integration, the stable operation of computer rooms is crucial. Traditional monitoring methods for computer room environment and power equipment mostly rely on manual inspections, which are not only labor-intensive and inefficient, but also difficult to achieve real-time monitoring, resulting in problems such as delayed response and insufficient early warning. If environmental conditions or power system failures occur during long-term operation of equipment, serious equipment damage and data loss may result. Therefore, it is necessary to adopt an advanced intelligent management system to manage computer rooms with data and provide better operational assurance. To this end, the applicant proposes a computer room power environment monitoring system based on sine cosine algorithm optimization processing according to actual needs. This monitoring system method monitors various power equipment and environmental parameters in the computer room in real time. The system introduces an optimization method based on sine cosine algorithm (SCA), which further improves the effectiveness and efficiency of data processing. Combined with intelligent alarms and automatic control, it effectively improves the safety and stability of computer room operation. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention proposes a data center power and environmental monitoring system based on sine and cosine algorithm optimization. The system comprises a data acquisition module, a processing module, an alarm module, an execution module, and a communication module. The system method involves the data acquisition module collecting and transmitting various power and environmental parameters within the data center. The processing module uses a sine and cosine algorithm optimization process to analyze the collected data and determine if any abnormalities exist within the data center. Upon detection of an anomaly, the alarm module promptly issues an alarm signal. Simultaneously, the execution module executes corresponding control operations based on instructions from the processing module. The communication module transmits monitoring data and alarm information to a remote monitoring center and the mobile devices of maintenance personnel, enabling timely processing of abnormal parameters. This achieves real-time monitoring of various power equipment and environmental parameters within the data center, realizing intelligent alarms and automatic control, and improving the safety and stability of data center operation.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] A data center power environment monitoring system based on sine and cosine algorithm optimization includes a data acquisition module, a processing module, an alarm module, an execution module, and a communication module. Its features are as follows:

[0006] Data acquisition module: Used to collect and transmit power and environmental parameters in the computer room. Various sensors installed in the computer room collect power and environmental parameters in real time and transmit them to the data acquisition module through the sensor network. After preprocessing, the data is sent to the processing module for analysis.

[0007] Processing module: Used to process and analyze the collected data and determine whether there are any abnormalities. The processing module performs real-time analysis of sensor data, judges abnormalities through intelligent analysis algorithms and preset thresholds, and generates alarm signals. The processing module summarizes the collected data every day, generates reports and trend charts, and provides data support for maintenance.

[0008] Alarm module: Used to issue alarm signals when an anomaly is detected. Based on the alarm signal, the alarm module notifies maintenance personnel through local audible and visual alarms and remote SMS, email, or mobile application. The alarm system integrates artificial intelligence analysis algorithms to analyze alarm data and improve accuracy.

[0009] Execution module: Based on the instructions from the processing module, it performs corresponding control operations, such as: automatically cutting off the power supply or activating the backup power supply when an abnormal voltage is detected; adjusting the air conditioner or starting the ventilation system when an abnormal temperature or humidity is detected; and recording operation logs for subsequent audit and analysis.

[0010] Communication module: Used to transmit monitoring data and alarm information to the remote monitoring center or maintenance personnel's mobile devices. The communication module transmits data and alarm information to the remote monitoring center and mobile devices via wired or wireless means. During transmission, encryption and security protocols are used to ensure data integrity and confidentiality. After transmission is completed, the data is synchronized, providing real-time data storage.

[0011] Furthermore, the data acquisition module of the computer room power and environment monitoring system based on sine and cosine algorithm optimization processes collects power parameters and environmental parameters. The sensors used for the power parameters and environmental parameters are specifically:

[0012] Power parameter sensor:

[0013] Voltage Sensors: Hall effect voltage sensors and opto-isolated voltage sensors are used. The Hall effect voltage sensor detects voltage changes using the Hall effect and has high stability. The opto-isolated voltage sensor isolates the voltage signal through an optocoupler, improving the system's anti-interference capability.

[0014] Current sensor: The system employs a Hall effect current sensor and a converter. The Hall effect current sensor uses the Hall effect principle to detect current and features high accuracy and rapid response. The converter converts high current into a low current signal through a current transformer for detecting large currents.

[0015] Power sensor: Employs an intelligent power sensor that converts voltage and current into power signals and transmits them to the processing module via a bus;

[0016] Environmental parameter sensors:

[0017] Temperature and humidity sensors: The system employs DHT22 and SHT31 temperature and humidity sensors. The DHT22 temperature and humidity sensor features high accuracy and can operate in environments ranging from -40℃ to 80℃, with a humidity range of 0-100%RH. The SHT31 temperature and humidity sensor features fast response and high accuracy, and integrates an I2C communication interface for easy data transmission.

[0018] Smoke Sensors: The system employs both the MQ-2 smoke sensor and a photoelectric smoke sensor. The MQ-2 smoke sensor is characterized by high sensitivity and excellent detection of changes in the concentration of combustible gases and smoke. The photoelectric smoke sensor detects the concentration of smoke particles through the principle of light scattering, further improving the accuracy of early warnings.

[0019] Water immersion sensor: It adopts both electrode-type water immersion sensor and capacitive water immersion sensor. The electrode-type water immersion sensor detects the water level by the change in resistance between electrodes, and the measurement is fast; the capacitive water immersion sensor uses the change in capacitance to monitor liquid seepage, and has strong anti-interference ability.

[0020] Vibration sensor: Determines equipment malfunctions by detecting abnormal vibrations;

[0021] Noise sensor: Used to monitor the noise level of equipment in the computer room and detect abnormal noises in the computer room in a timely manner.

[0022] Furthermore, the main functions of the processing module of the computer room power and environment monitoring system based on sine and cosine algorithm optimization include:

[0023] Real-time data processing: The received data is first preprocessed and filtered, then processed and analyzed to ensure its accuracy and timeliness. Algorithms used include:

[0024] Matched filtering: Identifies and extracts specific signal patterns, enhancing signal detection sensitivity;

[0025] Fast Fourier Transform: Converts a time-domain signal into a frequency-domain signal to analyze frequency components and identify periodic patterns and anomalies;

[0026] Anomaly detection and analysis: A built-in machine learning algorithm module quickly triggers alarms and diagnoses faults when data deviates from preset safety thresholds; the algorithms used include:

[0027] K-Means clustering algorithm: classifies sensor data and identifies outlier data points;

[0028] DBSCAN density clustering algorithm: By analyzing density distribution, it identifies outliers and noisy data, improving detection accuracy;

[0029] Data optimization algorithm: An optimization algorithm based on the Sine Cosine Algorithm (SCA) is used to further improve the effectiveness and efficiency of data processing.

[0030] Furthermore, the specific steps of the data optimization algorithm for the processing module of the computer room power and environment monitoring system based on sine and cosine algorithm optimization are as follows:

[0031] Step 1: Initialize the population:

[0032] Randomly generate a population containing n individuals, each with dimension d, and randomly distribute them within the search space;

[0033] formula:

[0034] [X_{i,j}=\text{random}(L,U)]

[0035] Where L and U are the lower and upper bounds of dimension j, respectively;

[0036] Step 2: Fitness Assessment

[0037] A fitness assessment is performed on each individual to evaluate their fitness.

[0038] Formula: [\text{fitness}_i=f(X_i)]

[0039] Step 3, Location Update:

[0040] Update the position of each individual based on sine and cosine functions;

[0041] formula:

[0042] [X_i(t+1)=X_i(t)+r_i\left[\alpha\sin(\beta)+\gamma\cos(\beta)\right]]

[0043] Where (X_i(t)) is the position of individual (i) at time (t), (r_i) is a random number, and (\alpha,\beta,\gamma) are dynamic parameters that control the step size and direction;

[0044] Step 4: Iterative execution:

[0045] The position is continuously updated and the fitness is evaluated iteratively until the maximum number of iterations is reached or the fitness no longer changes significantly.

[0046] Step 5: Select the optimal solution:

[0047] When the termination condition is met, return the best individual in the current population as the result.

[0048] Furthermore, the data optimization algorithm model of the processing module of the computer room power and environment monitoring system based on sine and cosine algorithm optimization is specifically as follows:

[0049] Population initialization: Randomly generate the initial population, and the individuals are randomly distributed within the search space;

[0050] Fitness assessment: Define a fitness function to assess each individual;

[0051] Position update: Dynamically adjust the individual position using sine and cosine functions;

[0052] Iterative updates: Continuously update the position and evaluate the fitness;

[0053] Selecting the optimal solution: At the end of the iteration, select the individual with the best fitness as the result.

[0054] The benefits of this application are:

[0055] 1. The data center power and environmental monitoring system based on sine and cosine algorithm optimization can realize real-time monitoring of power and environmental parameters and detect problems in advance;

[0056] 2. The computer room power and environment monitoring system based on sine and cosine algorithm optimization can detect abnormal parameters in a timely manner, automatically alarm, improve response speed, and avoid serious accidents;

[0057] 3. The data center power and environment monitoring system, based on sine and cosine algorithm optimization, can intelligently adjust the operating status of equipment to ensure stable operation;

[0058] 4. The data center power and environment monitoring system based on sine and cosine algorithm optimization can remotely transmit data, which facilitates monitoring and management, reduces maintenance costs, and adopts advanced encryption and secure transmission technology to ensure data security. Attached Figure Description

[0059] Figure 1 This is a schematic diagram of the monitoring system structure of the present invention;

[0060] Figure 2 This is a schematic diagram of the data acquisition module workflow of the present invention;

[0061] Figure 3 This is a schematic diagram of the analysis process of the processing module of the present invention;

[0062] Figure 4 This is a schematic diagram of the alarm module's workflow in this invention;

[0063] Figure 5 This is a schematic diagram of the control flow of the execution module of the present invention;

[0064] Figure 6 This is a schematic diagram of the data transmission process of the communication module of the present invention. Detailed Implementation

[0065] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments:

[0066] like Figure 1 As shown, this is a data center power and environment monitoring system based on sine and cosine algorithm optimization. The system includes a data acquisition module, a processing module, an alarm module, an execution module, and a communication module. Its features are:

[0067] Data acquisition module: Used to collect and transmit power and environmental parameters in the computer room. Various sensors installed in the computer room collect power and environmental parameters in real time and transmit them to the data acquisition module through the sensor network. After preprocessing, the data is sent to the processing module for analysis.

[0068] like Figure 2 As shown, the data acquisition module is one of the core components of the system, responsible for real-time acquisition of power and environmental parameters within the computer room, including monitoring of various parameters such as voltage, current, temperature, and humidity. We need to perform real-time monitoring and anomaly detection of these parameters to ensure the safe and stable operation of the equipment in the computer room. Data is transmitted to the processing module via bus protocols such as RS485, I2C, SPI, and Modbus. The sensors used for the power and environmental parameters are specifically:

[0069] Power parameter sensor:

[0070] Voltage Sensors: Hall effect voltage sensors and opto-isolated voltage sensors are used. The Hall effect voltage sensor detects voltage changes using the Hall effect and has high stability. The opto-isolated voltage sensor isolates the voltage signal through an optocoupler, improving the system's anti-interference capability.

[0071] Current sensor: The system employs a Hall effect current sensor and a converter. The Hall effect current sensor uses the Hall effect principle to detect current and features high accuracy and rapid response. The converter converts high current into a low current signal through a current transformer for detecting large currents.

[0072] Power sensor: Employs an intelligent power sensor that converts voltage and current into power signals and transmits them to the processing module via a bus;

[0073] Environmental parameter sensors:

[0074] Temperature and humidity sensors: The system employs DHT22 and SHT31 temperature and humidity sensors. The DHT22 temperature and humidity sensor features high accuracy and can operate in environments ranging from -40℃ to 80℃, with a humidity range of 0-100%RH. The SHT31 temperature and humidity sensor features fast response and high accuracy, and integrates an I2C communication interface for easy data transmission.

[0075] Smoke Sensors: The system employs both the MQ-2 smoke sensor and a photoelectric smoke sensor. The MQ-2 smoke sensor is characterized by high sensitivity and excellent detection of changes in the concentration of combustible gases and smoke. The photoelectric smoke sensor detects the concentration of smoke particles through the principle of light scattering, further improving the accuracy of early warnings.

[0076] Water immersion sensor: It adopts both electrode-type water immersion sensor and capacitive water immersion sensor. The electrode-type water immersion sensor detects the water level by the change in resistance between electrodes, and the measurement is fast; the capacitive water immersion sensor uses the change in capacitance to monitor liquid seepage, and has strong anti-interference ability.

[0077] Vibration sensor: Determines equipment malfunctions by detecting abnormal vibrations;

[0078] Noise sensors: Used to monitor the noise level of equipment operating in the computer room and promptly detect abnormal noises within the computer room.

[0079] Processing module: Used to process and analyze the collected data and determine whether there are any abnormalities. The processing module performs real-time analysis of sensor data, judges abnormalities through intelligent analysis algorithms and preset thresholds, and generates alarm signals. The processing module summarizes the collected data every day, generates reports and trend charts, and provides data support for maintenance.

[0080] like Figure 3 As shown, after receiving the data, the processing module needs to preprocess and filter it to ensure the accuracy and stability of the data; the following algorithm is used:

[0081]

[0082] Then, anomaly detection and optimization are performed. When processing and analyzing sensor data, a sine-cosine algorithm (SCA) is introduced to optimize the data and detect anomalies. The specific steps of the processing module are as follows:

[0083] Step 1: Real-time Data Processing: The received data is first preprocessed and filtered, then processed and analyzed to ensure its accuracy and timeliness. Algorithms used include:

[0084] Step 2, Matched Filtering: Identifying and extracting specific signal patterns to enhance signal detection sensitivity;

[0085] Step 3: Fast Fourier Transform: Convert the time-domain signal into a frequency-domain signal, analyze the frequency components, and identify periodic patterns and anomalies;

[0086] Step 4, Anomaly Detection and Analysis: The built-in machine learning algorithm module quickly triggers alarms and diagnoses faults when data deviates from preset safety thresholds. The algorithms used include:

[0087] K-Means clustering algorithm: classifies sensor data and identifies outlier data points;

[0088] DBSCAN density clustering algorithm: By analyzing density distribution, it identifies outliers and noisy data, improving detection accuracy;

[0089] Data optimization algorithm: An optimization algorithm based on the Sine Cosine Algorithm (SCA) is used to further improve the effectiveness and efficiency of data processing.

[0090] The specific steps of the optimization algorithm based on the Sine Cosine Algorithm (SCA) are as follows:

[0091] Step 1: Initialize the population:

[0092] Randomly generate a population containing n individuals, each with dimension d, and randomly distribute them within the search space;

[0093] formula:

[0094] [X_{i,j}=\text{random}(L,U)]

[0095] Where L and U are the lower and upper bounds of dimension j, respectively;

[0096] Algorithm code:

[0097] Python

[0098] import numpy as np

[0099] n=30# Population size

[0100] d = 10# Individual Dimension

[0101] L = -10# Lower limit

[0102] U=10# upper limit

[0103] X=np.random.uniform(L,U,(n,d))

[0104] ```

[0105] Step 2: Fitness Assessment

[0106] A fitness assessment is performed on each individual to evaluate their fitness.

[0107] Formula: [\text{fitness}_i=f(X_i)]

[0108] Algorithm code:

[0109]

[0110] Step 3, Location Update:

[0111] Update the position of each individual based on sine and cosine functions;

[0112] formula:

[0113] [X_i(t+1)=X_i(t)+r_i\left[\alpha\sin(\beta)+\gamma\cos(\beta)\right]]

[0114] Where (X_i(t)) is the position of individual (i) at time (t), (r_i) is a random number, and (\alpha,\beta,\gamma) are dynamic parameters that control the step size and direction;

[0115] Algorithm code:

[0116]

[0117]

[0118] Step 4: Iterative execution:

[0119] The position is continuously updated and the fitness is evaluated iteratively until the maximum number of iterations is reached or the fitness no longer changes significantly.

[0120] Algorithm code:

[0121]

[0122] Step 5: Select the optimal solution:

[0123] When the termination condition is met, return the best individual in the current population as the result;

[0124] Algorithm code:

[0125] Python

[0126] best_position=X[np.argmin(fitness)]

[0127] best_fitness=np.min(fitness).

[0128] The core of SCA lies in utilizing the properties of sine and cosine functions to update the individual's position, thereby finding the optimal solution in the search space. Its model can be described as follows:

[0129] Population initialization: Randomly generate the initial population, and the individuals are randomly distributed within the search space;

[0130] Fitness assessment: Define a fitness function to assess each individual;

[0131] Position update: Dynamically adjust the individual position using sine and cosine functions;

[0132] Iterative updates: Continuously update the position and evaluate the fitness;

[0133] Selecting the optimal solution: At the end of the iteration, select the individual with the best fitness as the result.

[0134] The processing module also possesses data storage and management capabilities, and it has multiple storage and management methods, specifically:

[0135] Historical data is stored using cloud databases or local databases (such as TSDB and SQLite), supporting multi-dimensional and multi-condition queries to provide a basis for maintenance and optimization; the system supports data backup and recovery to ensure data integrity and security.

[0136] Time Series Database (TSDB): Stores time series data for historical analysis and predictive maintenance;

[0137] SQLite database: A lightweight embedded database that stores system configurations and real-time data caching to ensure data persistence; rules engine.

[0138] With an integrated programmable rules engine, administrators can set and adjust control logic and thresholds according to specific scenarios; rules take effect instantly through the front-end interface, enabling the system to cope with changing operating environments.

[0139] Rule configuration interface: The graphical user interface (GUI) enables drag-and-drop rule setting and configuration of complex control logic;

[0140] Rule execution engine: Parses executable code and executes it in real time, ensuring timely and accurate system response.

[0141] Alarm module: Used to issue alarm signals when an anomaly is detected. Based on the alarm signal, the alarm module notifies maintenance personnel through local audible and visual alarms and remote SMS, email, or mobile application. The alarm system integrates artificial intelligence analysis algorithms to analyze alarm data and improve accuracy.

[0142] like Figure 4 After the processing module detects an abnormal situation, it sends an alarm signal to maintenance personnel through the alarm module, and at the same time generates corresponding control commands and transmits them to the execution module. For example, when parameters such as voltage, current, or temperature and humidity exceed preset safety thresholds, the system will issue an alarm and activate corresponding emergency measures. The algorithm code for this processing is as follows:

[0143]

[0144] The alarm module links local and remote alarm system devices, and can be specifically divided into:

[0145] Local alarm system:

[0146] Sound alarm: A buzzer is installed in the computer room to sound an alarm when an anomaly is detected; the volume and frequency can be adjusted according to the severity of the problem, with multiple alarm tone modes;

[0147] Light alarm: Uses LED indicator lights to emit light signals of different colors and flashing frequencies to indicate different levels of alarm information; red indicates a serious fault, yellow indicates a general warning, and the color and flashing pattern of the light alarm can be programmed.

[0148] Remote alarm system:

[0149] SMS alarm: The alarm information is sent to the mobile phone of maintenance personnel through the SMS gateway connected by the communication module. The alarm content includes the type of abnormality, time and parameters.

[0150] Email alerts: The mail server automatically sends alert emails, providing detailed reports of anomalies and related data. Email attachments are supported, including detailed reports and charts.

[0151] Mobile app alarms: A companion mobile app has been developed to send push notifications instantly when an anomaly is detected, ensuring timely response. The app features a real-time monitoring interface, providing device status, alarm logs, and historical data.

[0152] The alarm module is designed with low, medium, and high alarm levels. The system automatically selects the appropriate mode based on the situation to quickly and effectively handle problems. Alarm records are synchronously stored on a central server for querying and auditing.

[0153] Execution module: Based on the instructions from the processing module, it performs corresponding control operations, such as: automatically cutting off the power supply or activating the backup power supply when an abnormal voltage is detected; adjusting the air conditioner or starting the ventilation system when an abnormal temperature or humidity is detected; and recording operation logs for subsequent audit and analysis.

[0154] like Figure 5 As shown, the execution module operates the equipment in the computer room according to control commands, mainly including:

[0155] Power equipment control:

[0156] Power failure protection: Utilizing high-performance relays or switches, the system quickly disconnects power in case of abnormal power conditions or equipment overload to prevent damage. Backup power management ensures automatic switching in case of main power failure, allowing equipment to continue operating; a manual overwrite mode is also available.

[0157] Load regulation: When a power overload is detected, the load regulation module gradually shuts down non-critical loads to ensure the stable operation of core equipment. The batch load control function dynamically adjusts the load distribution to reduce power consumption.

[0158] Environmental equipment control:

[0159] Air conditioning control: Automatically adjusts the status of air conditioning equipment based on temperature and humidity data to maintain appropriate temperature and humidity, supports multiple air conditioners to work together, and balances power consumption and cooling effect;

[0160] Ventilation and smoke exhaust system: The smoke exhaust equipment is automatically activated when smoke or high temperature is detected to quickly reduce the concentration and temperature of harmful gases. The smoke exhaust system has multiple power adjustment levels and dynamically adjusts the air volume.

[0161] Emergency measures:

[0162] In extreme situations, such as fire or severe flooding, the system, according to the emergency plan, shuts down all electrical equipment and activates the emergency ventilation and smoke extraction systems to ensure personnel safety and minimize equipment damage. The emergency plan is regularly drilled and simulated to ensure reliability.

[0163] Emergency power outage plan: When a major fault is detected, the emergency power outage plan will be executed to ensure the safe shutdown of equipment;

[0164] Emergency ventilation mode: Activate high-efficiency ventilation equipment to maximize air circulation rate and quickly remove smoke and heat;

[0165] The execution module has a redundancy mechanism to ensure high reliability and stability. All control commands are fed back in real time to ensure that each control action is confirmed, and a logging system records operations and results for subsequent auditing and analysis.

[0166] Communication module: Used to transmit monitoring data and alarm information to the remote monitoring center or the mobile devices of maintenance personnel. The communication module transmits data and alarm information to the remote monitoring center and mobile devices via wired or wireless means. During the transmission process, encryption and security protocols are used to ensure data integrity and confidentiality. After the transmission is completed, the data is synchronized, providing real-time data storage.

[0167] like Figure 6As shown, the communication module is responsible for transmitting monitoring data and alarm information to the remote monitoring center and maintenance personnel's mobile devices, providing wired and wireless transmission methods to ensure transmission reliability; specifically:

[0168] Wired communication:

[0169] Ethernet communication: Standard Ethernet protocol and fiber optic network enable highly stable data transmission, suitable for large data volume and long-distance communication;

[0170] RS485 / RS232: Short-range multi-device communication, low-latency synchronization, multi-master and multi-slave mode enhances scalability and flexibility;

[0171] Wireless communication:

[0172] Wi-Fi communication: Supports the IEEE 802.11 protocol, covering wireless communication of devices within the data center, suitable for flexible scenarios; multiple SSIDs and VLANs support the isolation of different devices to ensure data security;

[0173] Mobile communication: Supports 4G / 5G networks and cellular networks for data transmission, ensuring data access and alarm information transmission across different geographical locations. Wide-area coverage and high-speed transmission optimize data transmission efficiency in remote internet environments;

[0174] Data encryption and transmission security are important components of communication modules, and they can be divided into:

[0175] Data encryption: Monitoring data is encrypted using AES-256 to prevent theft and tampering during transmission;

[0176] Transmission security protocol: The data link is encrypted using SSL / TLS protocol to ensure data integrity and confidentiality;

[0177] The communication module has data redundancy and message confirmation mechanisms, automatically retrying in case of transmission failure, and synchronizing offline data upon success to ensure consistency; end-to-end data integrity verification protects data from tampering and damage during transmission.

[0178] The application of the data center power and environment monitoring system based on sine and cosine algorithm optimization can effectively improve the efficiency and accuracy of data processing. Its advantages, such as strong global search capability, fast convergence speed, simple calculation, and high flexibility, make this algorithm an important tool for the processing module, providing strong technical support for ensuring the safe and stable operation of data center equipment. Through its effective global and local search capabilities, the sine and cosine algorithm enables the processing module to achieve higher accuracy and efficiency in data optimization and anomaly detection, providing strong technical support for the entire monitoring system.

[0179] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other way. Any modifications or equivalent changes made based on the technical essence of the present invention shall still fall within the scope of protection claimed by the present invention.

Claims

1. A data center power environment monitoring system based on sine and cosine algorithm optimization, comprising a data acquisition module, a processing module, an alarm module, an execution module, and a communication module, characterized in that: Data Acquisition Module: Used to collect and transmit power and environmental parameters within the computer room. Various sensors installed in the computer room collect these parameters in real time and transmit them to the data acquisition module via a sensor network. After preprocessing, the data is sent to the processing module for analysis. Processing Module: Used to process and analyze the collected data and determine if any anomalies exist. The processing module performs real-time analysis of the sensor data, using intelligent analysis algorithms and preset thresholds to identify anomalies and generate alarm signals. The processing module summarizes the collected data daily, generating reports and trend charts to provide data support for maintenance. Alarm Module: Used to issue alarm signals when an anomaly is detected. Based on the alarm signal, the alarm module activates local audible and visual alarms and remote SMS alerts. The system notifies maintenance personnel via email or mobile application; the alarm system integrates artificial intelligence analysis algorithms to analyze alarm data; the execution module executes corresponding control operations according to the instructions of the processing module, automatically cutting off the power supply or activating the backup power supply when abnormal voltage is detected; adjusting the air conditioning or starting the ventilation system when abnormal temperature and humidity are detected; and records operation logs for subsequent audit and analysis; the communication module transmits monitoring data and alarm information to the remote monitoring center or the mobile devices of maintenance personnel. The communication module transmits data and alarm information to the remote monitoring center and mobile devices via wired or wireless means, using encryption and security protocols during transmission to ensure data integrity and confidentiality, and synchronizing data after transmission to provide all-time data storage. The processing module includes the following functions: Real-time data processing: The received data is first preprocessed and filtered, then processed and analyzed to ensure its accuracy and timeliness. Algorithms used include: Matched filtering: Identifying and extracting specific signal patterns to enhance signal detection sensitivity; Fast Fourier Transform: Converting time-domain signals to frequency-domain signals, analyzing frequency components, and identifying periodic patterns and anomalies; Anomaly detection and analysis: A built-in machine learning algorithm module quickly performs alarm processing and fault diagnosis when the detected data deviates from a preset safety threshold. Algorithms used include: K-Means clustering algorithm: Classifying sensor data and identifying abnormal data points; DBSCAN density clustering algorithm: Identifying outliers and noisy data by analyzing density distribution, improving detection accuracy; Data optimization algorithm: An optimization algorithm based on sine and cosine algorithms to further improve the effectiveness and efficiency of data processing. The specific steps of the data optimization algorithm for the processing module of the computer room power environment monitoring system based on sine and cosine algorithm optimization are as follows: Step 1: Initialize the population: Randomly generate a population containing n individuals, each with dimension d, and randomly distributed within the search space; Formula: [X_{i,j}=\text{random}(L,U)] where L and U are the lower and upper bounds of dimension j, respectively; Step 2: Fitness evaluation: Evaluate the fitness of each individual; Formula: [\text{fitness}_i=f(X_i)] Step 3: Position update: Update the position of each individual according to the sine and cosine functions; Formula : [X_i(t+1)=X_i(t)+r_i\left[\alpha\sin(\beta)+\gamma\cos(\beta)\right]] where (X_i(t)) is the position of individual (i) at time (t), (r_i) is a random number, and (\alpha,\beta,\gamma) are dynamic parameters controlling the step size and direction; Step 4, Iterative execution: continuously iterate to update the position and evaluate the fitness until the maximum number of iterations is reached or the fitness no longer changes significantly; Step 5, Select the optimal solution: when the termination condition is met, return the best individual in the current population as the result.

2. The computer room power environment monitoring system based on sine and cosine algorithm optimization processing according to claim 1, characterized in that: The data acquisition module collects power parameters and environmental parameters. The sensors used for these parameters are as follows: Power parameter sensors: Voltage sensors: Hall effect voltage sensors and opto-isolated voltage sensors are used. The Hall effect voltage sensor detects voltage changes using the Hall effect; the opto-isolated voltage sensor isolates the voltage signal through an optocoupler, improving the system's anti-interference capability; Current sensors: Hall effect current sensors and converters are used. The Hall effect current sensor detects current using the Hall effect principle, featuring high accuracy and rapid response; the converter converts high current into low current signals through a current transformer for detecting large currents; Power sensors: Intelligent power sensors are used, converting voltage and current into power signals and transmitting them to the processing module via a bus; Environmental parameter sensors: Temperature and humidity sensors: DHT22 and SHT31 temperature and humidity sensors are used. The SHT31 temperature and humidity sensor features high accuracy, operates in environments ranging from -40℃ to 80℃, and has a humidity range of 0-100%RH. It boasts fast response and high accuracy, and integrates an I2C communication interface for easy data transmission. The smoke sensor utilizes both the MQ-2 and photoelectric smoke sensors. The MQ-2 sensor offers high sensitivity and excellent detection of changes in the concentration of combustible gases and smoke, while the photoelectric smoke sensor detects smoke particle concentration through the principle of light scattering, further improving the accuracy of early warnings. The water immersion sensor employs both electrode-type and capacitive-type sensors. The electrode-type sensor detects water level changes through changes in resistance between electrodes, providing rapid measurement. The capacitive-type sensor monitors liquid infiltration by utilizing changes in capacitance, offering strong anti-interference capabilities. The vibration sensor detects abnormal vibrations to identify equipment malfunctions. The noise sensor monitors the operating noise level of equipment in the computer room, promptly detecting abnormal noises.

3. The computer room power environment monitoring system based on sine and cosine algorithm optimization processing according to claim 1, characterized in that: The data optimization algorithm model of the processing module of the computer room power environment monitoring system based on sine and cosine algorithm optimization is as follows: Population initialization: Randomly generate an initial population, and individuals are randomly distributed in the search space; Fitness evaluation: Define a fitness function to evaluate each individual; Position update: Dynamically adjust the position of individuals using sine and cosine functions; Iterative update: Continuously iterate the position update and fitness evaluation; Select the optimal solution: At the end of the iteration, select the individual with the best fitness as the result.

Images