Online hydrogen energy UPS (Uninterrupted Power Supply) intelligent control method and related equipment

By acquiring and analyzing the external and internal environmental information of hydrogen energy UPS and dynamically adjusting the control strategy, the problems of slow response speed and low energy utilization efficiency of traditional systems are solved, and more efficient power management and lower operating costs are achieved.

CN118983470AActive Publication Date: 2024-11-19BEIJING HUAQING DAYUN HYDROGEN ENERGY TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411046451.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-19
Estimated Expiration
2044-08-01

AI Technical Summary

Technical Problem

Traditional hydrogen energy UPS systems have slow response speed in the event of power outage, low energy utilization efficiency, and lack real-time monitoring and prediction of external environment changes and internal needs, making it difficult to achieve refined management.

Method used

By obtaining external environment information and internal operating environment information, and determining comprehensive power outage risk information based on random forest models and other data analysis methods, the control strategy of hydrogen energy UPS is dynamically adjusted, including operating power and emergency response cycles.

Benefits of technology

It realizes the identification of potential power outage risks in advance, reduces power switching delays, optimizes energy efficiency and operating costs, and improves system adaptability and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983470A_ABST
    Figure CN118983470A_ABST
Patent Text Reader

Abstract

The invention discloses an online hydrogen energy UPS intelligent control method and related equipment, and relates to the field of intelligent control, and the method comprises the steps: obtaining the external environment information of a target online hydrogen energy UPS; acquiring internal operation environment information of a server corresponding to the target online hydrogen energy UPS serving as a standby power supply; acquiring external factor power-off risk information based on the external environment information; obtaining internal factor power-off risk information based on the internal operation environment information; determining comprehensive power-off risk information based on the external factor power-off risk information and the internal factor power-off risk information; determining a target control strategy based on the comprehensive power-off risk information; and controlling the target online hydrogen energy UPS based on the target control strategy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This specification relates to the field of intelligent control, and more specifically, to an online hydrogen UPS intelligent control method and related equipment. Background Art

[0002] While existing hydrogen-powered UPS (Uninterruptible Power Supply) applications have begun to leverage the advantages of hydrogen fuel cells, such as environmental friendliness and low operating costs, their startup and control strategies often rely on more traditional methods. Typically, these systems activate only after detecting a primary power failure and employ pre-set, fixed parameters to manage power switching and energy distribution.

[0003] This approach has the following limitations:

[0004] 1. Response speed: Traditional hydrogen UPS systems may experience delays when switching to backup power, especially when power risks are not predicted in advance.

[0005] 2. Energy efficiency: Fixed operating strategies may not be able to optimize the use of hydrogen fuel, especially under changing external environment and internal load conditions.

[0006] 3. Lack of forecasting: The lack of real-time monitoring and forecasting of external environmental changes (such as extreme weather or power grid instability) and internal demands (such as server load fluctuations) makes it difficult to achieve refined management. Summary of the Invention

[0007] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention of this application is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0008] In the first aspect, the present application proposes an online hydrogen UPS intelligent control method, which includes:

[0009] Obtain external environment information of the target online hydrogen UPS;

[0010] Obtaining internal operating environment information of the server corresponding to the target online hydrogen UPS as a backup power supply;

[0011] Acquiring external factor power outage risk information based on the external environment information;

[0012] Acquiring internal factor power outage risk information based on the internal operating environment information;

[0013] Determining comprehensive power outage risk information based on the external power outage risk information and the internal power outage risk information;

[0014] determining a target control strategy based on the comprehensive power outage risk information;

[0015] The target online hydrogen energy UPS is controlled based on the target control strategy.

[0016] In a feasible implementation manner, the external environmental information includes weather condition information, power grid status information and regional factor information, the internal environmental information includes server load information, system thermal management information and server aging information, and the target control strategy includes target operating power and emergency response cycle.

[0017] In a feasible implementation manner, obtaining the external factor power outage risk information based on the external environment information includes:

[0018] Fill missing values ​​and perform Z-score standardization on the weather condition information to obtain standardized weather condition information;

[0019] Performing missing value interpolation and minimum and maximum normalization operations on the power grid status information to obtain normalized power grid status information;

[0020] Performing a one-hot encoding operation on the regional factor information to obtain regional factor standardization information;

[0021] extracting weather condition features from the standardized weather condition information based on a time series analysis method;

[0022] extracting grid operation characteristics from the standardized information of grid conditions based on graph theory;

[0023] extracting regional factor features from the regional factor standardized information based on principal component analysis;

[0024] The external factor power outage risk information is obtained based on the weather condition characteristics, the power grid operation characteristics, the regional factor characteristics and the target random forest model.

[0025] In a feasible implementation manner, obtaining the external factor power outage risk information based on the weather condition characteristics, the power grid operation characteristics, the regional factor characteristics, and the target random forest model includes:

[0026] Performing a splicing operation on the weather condition characteristics, the power grid operation characteristics, and the regional factor characteristics to determine basic characteristics of the external environment;

[0027] In a case where at least two of the extracted weather condition features, the power grid operation features, and the regional factor features exceed their corresponding feature thresholds, generating an external environment binary feature corresponding to the external environment based on the external environment features exceeding the feature thresholds;

[0028] The external environment basic features and the external environment binary features are input into a target random forest model to obtain the external factor power outage risk information.

[0029] In a feasible implementation manner, obtaining the internal factor power outage risk information based on the internal operating environment information includes:

[0030] Preprocessing the server load information using a sliding window averaging method, and extracting load peak features from the processed server load information;

[0031] performing a normalization operation on the system thermal management information, and extracting a temperature anomaly frequency feature and a temperature change rate feature of the normalized system thermal management information;

[0032] determining an aging score feature and a maintenance and failure correlation feature based on the server aging information;

[0033] The load peak feature, temperature anomaly number feature, temperature change rate feature, aging score feature and maintenance and fault association feature are input into the target SVM classifier to obtain the internal factor power outage risk information.

[0034] In a feasible implementation manner, determining the comprehensive power outage risk information based on the external power outage risk information and the internal power outage risk information includes:

[0035] Obtain the geographic location information, server type information, and server backup information of the server corresponding to the target online hydrogen UPS as a backup power supply;

[0036] Determine, based on the geographic location information, the server type information, and the server backup information, first weight information corresponding to the external power outage risk information and second weight information corresponding to the internal power outage risk information;

[0037] Comprehensive power outage risk information is determined based on the first weight information, the second weight information, the external factor power outage risk information, and the internal factor power outage risk information.

[0038] In a feasible implementation manner, the first weight information w is determined based on the following formula: 外部 and the second weight information w 内部 :

[0039] W外部 =α·S 地理

[0040] W 内部 =β·S 类型 +γ·S 备份

[0041] α, β, γ are pre-set initial coefficients, S 地理 is the geographical location coefficient, S 类型 is the server type coefficient and S 备份 The server backup factor.

[0042] In a feasible implementation manner, the above-mentioned determination of the target control strategy based on the above-mentioned comprehensive power outage risk information includes:

[0043] When the comprehensive power outage risk information indicates a low risk, the target control strategy is low operating power and low emergency response cycle; and / or,

[0044] When the comprehensive power outage risk information is medium risk, the target control strategy is medium operating power and medium emergency response period; and / or,

[0045] When the comprehensive power outage risk information is high risk, the target control strategy is high operating power and high emergency response cycle.

[0046] In a second aspect, the present application further proposes an online hydrogen UPS intelligent control device, comprising:

[0047] A first acquisition unit is used to acquire external environment information of a target online hydrogen energy UPS;

[0048] The second acquisition unit is used to obtain the internal operating environment information of the server corresponding to the target online hydrogen energy UPS as a backup power supply;

[0049] a third acquiring unit, configured to acquire external factor power outage risk information based on the external environment information;

[0050] a fourth acquiring unit, configured to acquire internal factor power outage risk information based on the internal operating environment information;

[0051] a first determining unit, configured to determine comprehensive power outage risk information based on the external factor power outage risk information and the internal factor power outage risk information;

[0052] a second determining unit, configured to determine a target control strategy based on the comprehensive power outage risk information;

[0053] A control unit is used to control the target online hydrogen energy UPS based on the target control strategy.

[0054] In a third aspect, the present application further proposes an online hydrogen-powered UPS, comprising the online hydrogen-powered UPS intelligent control device as described in the second aspect.

[0055] In summary, the intelligent control method for an online hydrogen UPS in an embodiment of the present application includes: obtaining external environmental information of a target online hydrogen UPS; obtaining internal operating environmental information of the server corresponding to the target online hydrogen UPS as a backup power source; obtaining external power outage risk information based on the external environmental information; obtaining internal power outage risk information based on the internal operating environmental information; determining comprehensive power outage risk information based on the external and internal power outage risk information; determining a target control strategy based on the comprehensive power outage risk information; and controlling the target online hydrogen UPS based on the target control strategy. Compared to traditional hydrogen UPS systems, the method proposed in this embodiment of the application continuously monitors the external environment and internal operating status, enabling the system to identify potential power outage risks in advance, thereby enabling early warning and early start-up, reducing delays and potential service interruptions caused by power switching. Based on real-time risk assessment and operating environment data, the intelligent control strategy can dynamically adjust hydrogen fuel usage and power output to optimize energy efficiency and operating costs. The intelligent control method proposed in this application allows the system to flexibly adjust to changes in the external environment and internal demand fluctuations, improving the system's adaptability and reliability. By optimizing hydrogen fuel usage, environmental impact is reduced while also lowering energy consumption and operating costs.

[0056] The online hydrogen UPS intelligent control method proposed in this application, and other advantages, objectives and features of this application will be reflected in part through the following description, and in part will also be understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present description. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0058] Figure 1 A schematic diagram of the process of an online hydrogen UPS intelligent control method provided in an embodiment of the present application;

[0059] Figure 2 A schematic diagram of the structure of a user profile generation system based on user behavior provided in an embodiment of the present application;

[0060] Figure 3 This is a structural diagram of an online hydrogen UPS provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments.

[0062] See also Figure 1 , which is a flow chart of an online hydrogen UPS intelligent control method provided in an embodiment of the present application, which may specifically include:

[0063] S110, obtaining external environment information of the target online hydrogen energy UPS;

[0064] S120, obtaining the internal operating environment information of the server corresponding to the target online hydrogen UPS as a backup power supply;

[0065] S130, obtaining external factor power outage risk information based on the external environment information;

[0066] S140, obtaining internal factor power outage risk information based on the internal operating environment information;

[0067] S150, determining comprehensive power outage risk information based on the external power outage risk information and the internal power outage risk information;

[0068] S160: Determine a target control strategy based on the comprehensive power outage risk information;

[0069] S170: Control the target online hydrogen energy UPS based on the target control strategy.

[0070] For example, the system first collects information about the external environment surrounding the target online hydrogen UPS. This information may include local weather conditions, grid status, and other relevant regional factors. This data provides preliminary input for subsequent risk assessment.

[0071] The system obtains internal operating environment information of the target server using an online hydrogen UPS as a backup power source. This includes server load information, system thermal management information, and server aging information. This information helps assess the risk factors within the server that may cause power outages.

[0072] Based on the external environmental information collected in step S110, the power outage risk information of external factors is analyzed and obtained, as well as the prediction of extreme weather events, the analysis of power grid stability, and the impact of regional policy changes.

[0073] The server internal operating environment information collected in step S120 is analyzed to obtain power outage risk information of internal factors, including assessing potential power outage risks from aspects such as server load peak, system thermal abnormality, and device aging.

[0074] After obtaining external and internal outage risk information, this step combines these two pieces of information to form a comprehensive outage risk assessment. This comprehensive assessment will consider the impact of all relevant factors and provide decision support for subsequent control strategies.

[0075] Based on the comprehensive power outage risk information determined in step S150, this step will determine a set of target control strategies. This includes adjusting the target operating power and emergency response period of the online hydrogen UPS to optimize its performance and reduce the impact of power outages.

[0076] According to the target control strategy set in S160, the operation of the target online hydrogen UPS is actually controlled. This may include adjusting the output power of the backup power supply, changing the charging strategy of the backup power supply, or adjusting the emergency response operation.

[0077] In summary, compared with the traditional hydrogen UPS system, the method proposed in the embodiment of the present application can identify potential power outage risks in advance by continuously monitoring the external environment and internal operating status, thereby achieving early warning and early startup, reducing delays and potential service interruptions caused by power switching. Based on real-time risk assessment and operating environment data, the intelligent control strategy can dynamically adjust the use of hydrogen fuel and power output to optimize energy efficiency and operating costs. The intelligent control method proposed in this application allows the system to be flexibly adjusted according to changes in the external environment and fluctuations in internal demand, thereby improving the adaptability and reliability of the system. By optimizing the use of hydrogen fuel, the environmental impact is reduced while energy consumption and operating costs are reduced.

[0078] In some examples, the external environmental information includes weather condition information, power grid status information, and regional factor information, the internal environmental information includes server load information, system thermal management information, and server aging information, and the target control strategy includes target operating power and emergency response cycle.

[0079] For example, the external environment information of the target online hydrogen UPS is collected to evaluate the external factors that may affect the operation of the UPS. Specifically, it includes:

[0080] Weather condition information: Monitors temperature, humidity, wind speed, and other meteorological conditions, with particular attention to extreme weather events that could affect grid stability and equipment operation.

[0081] Grid status information: Analyze the stability of the grid power supply, including grid load, frequency fluctuations, and historical power outage data, to assess the potential impact of grid failures on the UPS.

[0082] Regional factor information: Consider region-specific policies, economic activities, and construction projects, which may indirectly affect electricity supply and demand.

[0083] Obtain the internal operating environment information of the server corresponding to the UPS as a backup power supply. The key points include:

[0084] Server load information: Real-time monitoring of server CPU usage, memory usage, and network traffic to identify the risk of power outages caused by excessive operating load.

[0085] System thermal management information: Monitors the temperature and cooling efficiency of the server room. High temperatures or insufficient cooling system efficiency may increase the risk of equipment failure and power outages.

[0086] Server aging information: Records the age and maintenance history of server hardware. Aging hardware is more likely to fail, thus affecting the normal power supply of the UPS.

[0087] Based on the collected external and internal environmental information, appropriate target control strategies are determined to optimize the response and operating efficiency of the hydrogen UPS. Specific control strategies include:

[0088] Target operating power: Adjusts the UPS output power based on real-time environmental information and system status to meet the actual needs of the server and maximize energy efficiency.

[0089] Emergency response cycle: Set and adjust the emergency response time period to ensure that the UPS can quickly and effectively provide necessary power support when power is suddenly interrupted.

[0090] Through this integrated intelligent control approach, the Target Online Hydrogen UPS is able to achieve efficient and reliable power management based on complex and changing environmental conditions and internal requirements. This strategy not only enhances the system's adaptability and reliability, but also optimizes energy use and reduces operating costs.

[0091] In some examples, obtaining external factor power outage risk information based on the external environment information includes:

[0092] Fill missing values ​​and perform Z-score standardization on the weather condition information to obtain standardized weather condition information;

[0093] Performing missing value interpolation and minimum and maximum normalization operations on the power grid status information to obtain normalized power grid status information;

[0094] Performing a one-hot encoding operation on the regional factor information to obtain regional factor standardization information;

[0095] extracting weather condition features from the standardized weather condition information based on a time series analysis method;

[0096] extracting grid operation characteristics from the standardized information of grid conditions based on graph theory;

[0097] extracting regional factor features from the regional factor standardized information based on principal component analysis;

[0098] The external factor power outage risk information is obtained based on the weather condition characteristics, the power grid operation characteristics, the regional factor characteristics and the target random forest model.

[0099] For example, missing values ​​are filled in the collected weather condition information to ensure data integrity. Z-score normalization is then performed. This normalizes the data by calculating the number of standard deviations between the data points and the mean, so that the processed weather condition information has a standardized distribution, facilitating subsequent analysis.

[0100] Missing values ​​in the grid status information are interpolated to fill in the data gaps. Then, the minimum and maximum normalization methods are applied to adjust the grid status information to the range of 0 to 1 to unify the scale of each data indicator.

[0101] Perform one-hot encoding on regional factor information to convert categorical variables into numerical binary variables, which helps to better process and analyze this information in subsequent machine learning models.

[0102] Time series analysis is applied to analyze the standardized weather condition information to identify important weather characteristics that may affect power supply, such as temperature fluctuations and the frequency of extreme meteorological events.

[0103] Graph theory is used to analyze the structure and connectivity of the power grid, thereby identifying key nodes and potential vulnerable points in the grid. These features help predict possible failure points in the grid.

[0104] The one-hot encoded data of regional factors were processed by principal component analysis (PCA) to extract the main components, which reflect the most influential variables in the regional factors.

[0105] The extracted weather condition features, grid operation characteristics, and regional factor characteristics are combined and input into a pre-trained random forest model. The random forest model uses these features to predict and assess the risk of power outages caused by external environmental factors. The model outputs a score for the risk of power outages caused by external factors, providing a scientific basis for subsequent decision-making.

[0106] In some examples, obtaining the external factor power outage risk information based on the weather condition characteristics, the power grid operation characteristics, the regional factor characteristics, and the target random forest model includes:

[0107] Performing a splicing operation on the weather condition characteristics, the power grid operation characteristics, and the regional factor characteristics to determine basic characteristics of the external environment;

[0108] In a case where at least two of the extracted weather condition features, the power grid operation features, and the regional factor features exceed their corresponding feature thresholds, generating an external environment binary feature corresponding to the external environment based on the external environment features exceeding the feature thresholds;

[0109] The external environment basic features and the external environment binary features are input into a target random forest model to obtain the external factor power outage risk information.

[0110] For example, the system first extracts features from the various types of external environmental information collected. This includes features extracted from weather conditions (such as temperature fluctuations, frequency of extreme weather events, etc.), features extracted from grid operation information (such as grid load fluctuations, frequent power fluctuations, etc.), and features extracted from regional factor information (such as policy changes, regional construction activities, etc.). These features will then be spliced ​​into a unified feature vector, called the external environment basic feature, which integrates all key external environmental data and provides basic data for subsequent risk assessment.

[0111] Based on the extracted weather condition features, grid operation features, and regional factor features, specific logical rules are applied to identify high-risk situations. For example, if the regional factor features show that the maintenance schedule in a certain area frequently exceeds the set threshold, and the weather condition features indicate the presence of extreme weather events such as typhoons or heavy rains, then the combination of these conditions will be considered a high-risk state. For this situation, the system creates a binary feature (for example, named "high-risk state") with a value of 1 (indicating high risk) or 0 (indicating normal risk).

[0112] The combined external environment basic features and the binary features generated by combining the conditions are input into the target random forest model. The random forest model analyzes these features to assess and predict the risk of power outages caused by external factors. The risk score or probability value output by the model is used to determine whether further preventive or emergency measures are necessary.

[0113] The embodiments of this application not only effectively utilize data extracted from multiple sources, but also enhance the accuracy and reliability of risk prediction through conditional combination logic. This intelligent risk management strategy can help online hydrogen UPS systems better cope with potential power outages and ensure the continued operation of critical facilities.

[0114] In some examples, obtaining the internal factor power outage risk information based on the internal operating environment information includes:

[0115] Preprocessing the server load information using a sliding window averaging method, and extracting load peak features from the processed server load information;

[0116] performing a normalization operation on the system thermal management information, and extracting a temperature anomaly frequency feature and a temperature change rate feature of the normalized system thermal management information;

[0117] determining an aging score feature and a maintenance and failure correlation feature based on the server aging information;

[0118] The load peak feature, temperature anomaly number feature, temperature change rate feature, aging score feature and maintenance and fault association feature are input into the target SVM classifier to obtain the internal factor power outage risk information.

[0119] For example, a sliding window averaging method is used to pre-process the server load information. This method helps smooth short-term fluctuations by averaging the server load data within a certain time window, thereby more accurately reflecting the server load trend.

[0120] The processed server load information is analyzed to extract load peak characteristics. Load peak refers to the highest load value recorded within a specific time window. This characteristic can indicate when the server may be at risk of overload.

[0121] Normalize the system thermal management information and standardize the temperature data to a unified scale (such as between 0 and 1) to eliminate the impact of different measurement equipment or standards.

[0122] The key features of the normalized system thermal management information are extracted, including the temperature anomaly count feature (recording the number of times the temperature exceeds the preset threshold) and the temperature change rate feature (measuring the speed or amplitude of the temperature change).

[0123] An aging score is calculated based on the server's age, maintenance frequency, and failure history. This score reflects the risk of performance degradation or failure due to aging. The relationship between maintenance records and failures is analyzed, and features are extracted to assess the effectiveness of maintenance measures and the reliability of server components.

[0124] The extracted load peak features, temperature anomaly count features, temperature change rate features, aging score features, and maintenance and fault correlation features are integrated and input into the target support vector machine (SVM) classifier. The SVM classifier analyzes these features to predict the risk of power outages caused by internal server factors. The risk assessment output by the SVM classifier guides further risk management measures, ensuring that the system can proactively prepare for and effectively respond to potential power outages.

[0125] In some examples, determining the comprehensive power outage risk information based on the external power outage risk information and the internal power outage risk information includes:

[0126] Obtain the geographic location information, server type information, and server backup information of the server corresponding to the target online hydrogen UPS as a backup power supply;

[0127] Determine, based on the geographic location information, the server type information, and the server backup information, first weight information corresponding to the external power outage risk information and second weight information corresponding to the internal power outage risk information;

[0128] Comprehensive power outage risk information is determined based on the first weight information, the second weight information, the external factor power outage risk information, and the internal factor power outage risk information.

[0129] For example, first, the system needs to collect key information about the server corresponding to the target online hydrogen UPS as a backup power supply, including:

[0130] Geographic location information involves the geographical area where the server is located, the stability of the local power grid, and whether it is often affected by natural disasters (such as earthquakes, floods, etc.).

[0131] Server type information, which details the server's specifications, performance, and technology type to assess its reliability and fault tolerance in specific situations.

[0132] Server backup information, analyze the configuration of the backup system, including the frequency, integrity and recovery capabilities of the backup.

[0133] Based on the information obtained, two weight information are determined:

[0134] The first weight information w 外部 It is based on the weight of the geographical location information and reflects the impact of external environmental factors (such as power grid instability, natural disasters, etc.) on the risk of power outages.

[0135] The second weight information w 内部 It is based on the weight of server type information and server backup information, reflecting the impact of internal factors (such as hardware reliability, robustness of backup system, etc.) on power outage risk.

[0136] External factor power outage risk information R 外部 It is a risk assessment based on a comprehensive analysis of external environmental factors such as weather conditions, power grid conditions and regional factors.

[0137] Internal factor power outage risk information R 内部 It is a risk assessment based on the server's operating environment information, such as the server's load condition, thermal management efficiency, hardware aging and other internal factors.

[0138] Combining the above information, the following formula can be used to calculate the comprehensive power outage risk information:

[0139] R 综合 =w 外部 ×R 外部 +w 内部 ×R 内部

[0140] Among them, R 综合 Represents the overall power outage risk score based on a comprehensive consideration of external and internal risk factors.

[0141] The method provided in this embodiment can more accurately assess and predict risk factors that may affect UPS system performance, thereby formulating more effective backup power management and emergency response strategies. The advantage of this method is that it allows for detailed analysis and trade-offs of various risk factors, ensuring that the UPS system can reliably provide support at critical moments.

[0142] In some examples, the first weight information w is determined based on the following formula: 外部 and the second weight information w 内部 :

[0143] W 外部 =α·S 地理

[0144] W 内部 =β·S 类型 +γ·S 备份

[0145] α, β, γ are pre-set initial coefficients, Sgeo is the geographic location coefficient, Stype is the server type coefficient, and Sbackup is the server backup coefficient.

[0146] For example, the initial coefficients (α, β, γ) represent the relative importance of different factors in the weight calculation. For example, α may represent the importance of geographic location, β represents the importance of server type, and γ represents the importance of server backup configuration.

[0147] Geographical location coefficient S 地理 Used to quantify the contribution of geographic location to the risk of power outage. High-risk areas (such as disaster-prone areas) will have higher S 地理 .

[0148] Server type coefficient S 类型 Reflects the impact of different types of servers on system stability due to their design and functional differences.

[0149] Server backup factor S 备份 Evaluate the performance and reliability of the backup system. High-quality and frequent backup operations will have higher S 备份 value.

[0150] Based on the above definitions of coefficients and weights, we can calculate the first weight information w 外部 and the second weight information w 内部 .

[0151] The calculation formula is as follows:

[0152] The first weight information w 外部 =α×S 地理 The impact of geographical location is directly amplified or reduced through the α coefficient to reflect its weight in external risk assessment.

[0153] The second weight information w 内部 =β×S 类型 +γ×S 备份 This formula combines the effects of server type and backup configuration, adjusting the contribution of these two factors through the β and γ coefficients respectively.

[0154] To ensure that the weight information is used in an appropriate range (such as between 0 and 1), it is necessary to 外部 and w 内部 Perform normalization processing.

[0155] The method provided in this embodiment can scientifically assess and integrate the specific contributions of the external environment and internal configuration to server power outage risk, providing data support for developing more precise risk management strategies. The application of this weighted calculation method helps optimize UPS system backup power management and enhance overall system stability and reliability.

[0156] In some examples, determining the target control strategy based on the comprehensive power outage risk information includes:

[0157] When the comprehensive power outage risk information indicates a low risk, the target control strategy is low operating power and low emergency response cycle; and / or,

[0158] When the comprehensive power outage risk information is medium risk, the target control strategy is medium operating power and medium emergency response period; and / or,

[0159] When the comprehensive power outage risk information is high risk, the target control strategy is high operating power and high emergency response cycle.

[0160] For example, in low-risk situations, the target control strategy is set to low operating power and a short emergency response period. When the external and internal environments are relatively stable and the possibility of power outages is low, the hydrogen UPS will operate at a lower power level, reducing energy consumption and extending equipment life, while also reducing the demand for emergency response resources.

[0161] In medium-risk scenarios, the target control strategy is set to medium operating power and medium emergency response period. In this case, due to the uncertainty of external or internal factors, the hydrogen UPS will adjust to medium power operation to quickly respond to possible changes in power demand while maintaining system efficiency and response speed.

[0162] In high-risk situations, the target control strategy is set to high operating power and a long emergency response cycle. When the comprehensive power outage risk information indicates a high risk, it indicates that a serious power supply problem may occur. In this case, the hydrogen UPS needs to operate at high power to ensure continuous power supply to critical loads and shorten the response cycle to immediately respond to sudden power outages.

[0163] Based on the target control strategy described above, the system will automatically adjust its parameters and settings to match the current risk situation. This includes, but is not limited to, power output adjustments, the readiness of backup power sources, and the priority and speed of communications with critical infrastructure.

[0164] In this way, the hydrogen UPS's intelligent control system dynamically adjusts its operating status and response measures based on comprehensive, real-time assessments of outage risk. This not only optimizes energy use and reduces operating costs, but also enhances system reliability and efficiency across varying risk levels. This strategic implementation ensures the high security and functionality of critical equipment during power instability.

[0165] In a second aspect, the present application further proposes an online hydrogen UPS intelligent control device 20, comprising:

[0166] The first acquisition unit 21 is used to acquire external environment information of the target online hydrogen energy UPS;

[0167] The second acquisition unit 22 is used to obtain the internal operating environment information of the server corresponding to the target online hydrogen energy UPS as a backup power supply;

[0168] A third acquiring unit 23 is configured to acquire external factor power outage risk information based on the external environment information;

[0169] A fourth acquiring unit 24 is configured to acquire internal factor power outage risk information based on the internal operating environment information;

[0170] A first determining unit 25 is configured to determine comprehensive power outage risk information based on the external power outage risk information and the internal power outage risk information;

[0171] A second determining unit 26 is configured to determine a target control strategy based on the comprehensive power outage risk information;

[0172] The control unit 27 is configured to control the target online hydrogen UPS based on the target control strategy.

[0173] In a third aspect, the present application further proposes an online hydrogen UPS 200, comprising the online hydrogen UPS intelligent control device 20 as described in the second aspect.

[0174] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0175] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0176] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0177] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0179] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of predicting the decomposition rate in alumina production in the corresponding embodiment.

[0180] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0181] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0183] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0184] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0185] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0186] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An online hydrogen UPS intelligent control method, comprising: Obtain external environment information of the target online hydrogen energy UPS; Obtaining the internal operating environment information of the server corresponding to the target online hydrogen energy UPS as a backup power supply; Acquiring external factor power outage risk information based on the external environment information; Acquiring internal factor power failure risk information based on the internal operating environment information; Determine comprehensive power outage risk information based on the external factor power outage risk information and the internal factor power outage risk information; Determining a target control strategy based on the comprehensive power outage risk information; The target online hydrogen energy UPS is controlled based on the target control strategy.

2. The online hydrogen UPS intelligent control method according to claim 1 is characterized in that: The external environment information includes weather condition information, power grid status information and regional factor information, the internal environment information includes server load information, system thermal management information and server aging information, and the target control strategy includes target operating power and emergency response cycle.

3. The online hydrogen UPS intelligent control method according to claim 2 is characterized in that: The acquiring the external factor power outage risk information based on the external environment information includes: Fill missing values ​​and perform Z-score standardization operations on the weather condition information to obtain standardized weather condition information; Performing missing value interpolation and minimum and maximum normalization operations on the power grid status information to obtain normalized power grid status information; Performing a one-hot encoding operation on the regional factor information to obtain regional factor standardization information; Extracting weather condition features from the weather condition standardized information based on a time series analysis method; Extracting grid operation characteristics from the grid status standardized information based on graph theory; Extracting regional factor features from the regional factor standardized information based on principal component analysis; The external factor power outage risk information is obtained based on the weather condition characteristics, the power grid operation characteristics, the regional factor characteristics and the target random forest model.

4. The online hydrogen UPS intelligent control method according to claim 3 is characterized in that: The step of obtaining the external factor power outage risk information according to the weather condition characteristics, the power grid operation characteristics, the regional factor characteristics and the target random forest model includes: Performing a splicing operation on the weather condition characteristics, the power grid operation characteristics and the regional factor characteristics to determine the basic characteristics of the external environment; In the case where at least two of the extracted weather condition features, the power grid operation features and the regional factor features exceed their corresponding feature thresholds, generating an external environment binary feature corresponding to the external environment based on the external environment features exceeding the feature thresholds; The external environment basic features and the external environment binary features are input into a target random forest model to obtain the power outage risk information of the external factors.

5. The online hydrogen UPS intelligent control method according to claim 2 is characterized in that: The obtaining the internal factor power failure risk information based on the internal operating environment information includes: Preprocessing the server load information using a sliding window averaging method, and extracting load peak features from the processed server load information; Performing a normalization operation according to the system thermal management information, and extracting a temperature anomaly frequency feature and a temperature change rate feature of the normalized system thermal management information; Determining an aging score feature and a maintenance and failure association feature based on the server aging information; The load peak feature, temperature anomaly number feature, temperature change rate feature, aging score feature and maintenance and fault association feature are input into the target SVM classifier to obtain the internal factor power outage risk information.

6. The online hydrogen UPS intelligent control method according to claim 2 is characterized in that: The determining of comprehensive power outage risk information based on the external factor power outage risk information and the internal factor power outage risk information includes: Obtaining geographical location information, server type information, and server backup information of the server corresponding to the target online hydrogen energy UPS as a backup power supply; Determine, based on the geographical location information, the server type information, and the server backup information, first weight information corresponding to the external factor power outage risk information and second weight information corresponding to the internal factor power outage risk information; Comprehensive power outage risk information is determined based on the first weight information, the second weight information, the external factor power outage risk information, and the internal factor power outage risk information.

7. The online hydrogen UPS intelligent control method according to claim 6 is characterized in that: The first weight information w is determined based on the following formula 外部 and the second weight information w 内部 : W external = α·S geography W internal = β·S type + ·S backup α, β, γ are the preset initial coefficients, S 地理 is the geographic location coefficient, S 类型 is the server type coefficient and S 备份 The server backup factor.

8. The online hydrogen UPS intelligent control method according to claim 2 is characterized in that: The determining of a target control strategy based on the comprehensive power outage risk information includes: When the comprehensive power outage risk information is low risk, the target control strategy is low operating power and low emergency response cycle; and / or, When the comprehensive power outage risk information is medium risk, the target control strategy is medium operating power and medium emergency response cycle; and / or, When the comprehensive power outage risk information is high risk, the target control strategy is high operating power and high emergency response cycle.

9. An online hydrogen UPS intelligent control device, characterized in that: include: A first acquisition unit is used to acquire external environment information of a target online hydrogen energy UPS; The second acquisition unit is used to acquire the internal operating environment information of the server corresponding to the target online hydrogen energy UPS as a backup power supply; A third acquisition unit, configured to acquire external factor power outage risk information based on the external environment information; A fourth acquisition unit, configured to acquire internal factor power failure risk information based on the internal operating environment information; A first determining unit, configured to determine comprehensive power outage risk information based on the external factor power outage risk information and the internal factor power outage risk information; A second determining unit, configured to determine a target control strategy based on the comprehensive power outage risk information; A control unit is used to control the target online hydrogen energy UPS based on the target control strategy.

10. An online hydrogen UPS, characterized in that: It comprises the online hydrogen energy UPS intelligent control device as described in claim 9.

Citation Information

Patent Citations

  • Uninterrupted power supply method and device of hydrogen fuel cell and hydrogen fuel cell

    CN111697253A

  • Uninterruptible power supply device for hydrogen fuel cell

    CN217720814U

  • Hybrid control methods for uninterruptible power supplies

    US20160334850A1