Energy-saving management system data analysis method, device, equipment and medium

Abstract

The invention provides an energy-saving management system data analysis method and device, equipment and a medium, is applied to a data center, and relates to the technical field of data processing. The method comprises the following steps: acquiring energy-saving data of each energy-saving module in an energy-saving management system of a data center, comparing the energy-saving data of each energy-saving module with historical energy-saving data of each energy-saving module, determining an energy consumption ratio change trend of electric equipment managed by each energy-saving module, and according to the energy consumption ratio change trend of the electric equipment corresponding to each energy-saving module, determining the energy consumption ratio of the electric equipment managed by each energy-saving module. And judging whether a network attack occurs or not, and performing harmfulness evaluation on the network attack occurring on the target energy-saving module when determining that the target energy-saving module has the network attack. By monitoring and comparing the real-time and historical energy consumption data of each energy-saving module, the energy use efficiency can be optimized, and the energy consumption trend can be predicted. And meanwhile, potential network attacks are detected by utilizing the change trend of the energy consumption ratio, so that the safety protection of the data center is facilitated.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a data analysis method, device, equipment and medium for an energy-saving management system. Background Art

[0002] With the rapid development of information technology, data centers, as key infrastructure supporting emerging businesses such as cloud computing and big data, are becoming increasingly important in modern society. However, as the scale of data centers continues to expand, their energy consumption issues are becoming increasingly prominent, becoming one of the important factors restricting the sustainable development of data centers. Traditional data center energy management methods often focus on the optimization of a single device or system, lacking comprehensive monitoring and analysis of the energy consumption of the entire data center, making it difficult to achieve effective resource allocation and energy consumption optimization.

[0003] In the operation of data centers, air conditioning systems, wind-moving thermal management systems, information technology (IT) equipment, and power distribution systems are the main sources of energy consumption. These systems not only directly affect the power usage effectiveness (PUE) of data centers, but also play an important role in maintaining the stability of the internal environment of data centers and ensuring the normal operation of IT equipment.

[0004] When managing and optimizing energy consumption for data centers, it is necessary to obtain energy-saving data from energy-saving management systems related to the above-mentioned electrical equipment in a timely manner. However, most existing solutions are post-processing modes, that is, a large amount of original energy-saving data is collected first and then stored and analyzed offline, which cannot meet the needs of application scenarios with high real-time requirements. Moreover, most energy-saving measures are implemented on specific electrical equipment, and different types of electrical equipment are not included in a unified scope for comprehensive consideration, thus limiting the overall optimization effect of the energy-saving management system. In addition, as network security threats continue to escalate, malicious network attacks against data centers occur from time to time, and existing energy-saving management systems generally lack effective security protection mechanisms and hazard assessment mechanisms to resist the above risks.

[0005] In view of this, it is necessary to propose a data analysis method for energy-saving management system to effectively cope with the above challenges and further improve the energy-saving efficiency and safety of data centers. Summary of the invention

[0006] The present application provides a data analysis method, device, equipment and medium for an energy-saving management system, which optimizes energy efficiency and predicts energy consumption trends by monitoring and comparing real-time and historical energy consumption data of each energy-saving module. At the same time, it uses energy consumption ratio changes to detect potential network attacks and enhance the security protection of data centers.

[0007] In the first aspect, the present application provides a data analysis method for an energy-saving management system, which is applied to a data center. The method includes: obtaining energy-saving data of each energy-saving module in the energy-saving management system of the data center, the energy-saving data including power consumption and power consumption, comparing the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module, determining the change trend of the energy consumption ratio of the power-consuming equipment managed by each energy-saving module, the energy consumption ratio being the ratio of the power consumed by the power-consuming equipment to the overall power consumption of the data center, judging whether a network attack has occurred based on the change trend of the energy consumption ratio of the power-consuming equipment corresponding to each energy-saving module, and when it is determined that a network attack has occurred on the target energy-saving module, performing a hazard assessment on the network attack on the target energy-saving module, the target energy-saving module being any energy-saving module among the energy-saving modules.

[0008] By continuously monitoring and analyzing the power consumption and power consumption of each energy-saving module, abnormal energy consumption can be discovered in a timely manner, and measures can be taken to optimize energy efficiency. Based on the comparison of historical data and current data, the trend of energy consumption ratio changes can be accurately obtained. Once an energy-saving module is identified as being attacked by a network, a hazard assessment can be quickly carried out to further improve the energy-saving efficiency and safety of the data center.

[0009] As a possible implementation method, the energy-saving data of each energy-saving module is compared with the historical energy-saving data of each energy-saving module to determine the change trend of the energy consumption ratio of the electrical equipment managed by each energy-saving module, specifically including: taking at least one historical energy-saving data of each energy-saving module and the currently acquired energy-saving data as a data set, taking the average value of the energy-saving data in the data set as a set data threshold, and determining the change trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module according to the number of energy-saving data above and below the set data threshold in the data set.

[0010] By comparing the average value of current data with historical data, we can find out which modules have significant changes in energy consumption, so that we can take measures to deal with potential problems. Based on detailed energy consumption data analysis, we can more accurately understand the performance of each energy-saving module, so as to carry out more refined energy management and optimization. By continuously tracking the trend of energy consumption ratio changes, we can help predict future energy consumption, so as to provide a basis for formulating long-term energy-saving strategies. After obtaining the trend of energy consumption ratio changes, we can adjust the operating parameters or update the hardware of energy-saving equipment according to the specific situation to achieve a higher energy efficiency level and reduce the PUE value of the data center.

[0011] As a possible implementation method, whether a network attack occurs is judged according to the changing trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module, specifically including: when it is determined that the changing trend of the energy consumption ratio of the electrical equipment corresponding to the target energy-saving module deviates from the set changing range, the energy-saving data of the target energy-saving module is input into a network attack judgment model, the network attack judgment model is trained based on the energy-saving data of the energy-saving module that is attacked by the network, and the network attack judgment model is used to extract feature information related to the network attack in the energy-saving data of the target energy-saving module, and determine the type of network attack suffered by the target energy-saving module according to the feature information related to the network attack.

[0012] By inputting energy-saving data into a network attack judgment model trained based on historical data of network attacks, data centers can effectively detect and classify network attacks, thereby improving the security of the system and helping data centers to promptly detect and respond to potential security threats.

[0013] As a possible implementation method, at least one type of network attack type includes: a forged attack type, a substitution attack type, a replay attack type, and a ransomware attack type.

[0014] As a possible implementation method, the network attack judgment model is used to extract characteristic information related to network attacks in the energy-saving data of the target energy-saving module, specifically including: converting the characteristic information related to network attacks in the energy-saving data of the target energy-saving module into dictionary structure data, and the network attack judgment model outputs the network attack type in text form based on the dictionary structure data.

[0015] By basing the model on relevant dictionary data rather than large-scale inspection data, the risk of large language models generating erroneous or irrelevant content can be reduced, which helps improve the accuracy of generated text. In addition, large language models can better understand the context and provide more precise results. Compared with directly querying and associating data from raw logs, the process of extracting corresponding data values ​​is simpler and more efficient, reducing the complexity and time cost of data processing.

[0016] As a possible implementation method, when it is determined that a target energy-saving module has been attacked by a network, a hazard assessment is performed on the network attack on the target energy-saving module, specifically including: determining the potential risk level corresponding to the type of network attack on the target energy-saving module according to a risk assessment model, wherein the risk assessment model is used to evaluate the potential risk level of each type of network attack, marking the potential risk level on the energy-saving data of the target energy-saving module, and updating and training the network attack judgment model using the energy-saving data marked with the potential risk level. Perform evaluation and comparison on the answers in text form to obtain results with quality scores or risk levels.

[0017] By using a risk assessment model, the potential risk level of different cyber attack types can be more accurately assessed, helping data center managers better understand the impact of an attack.

[0018] As a possible implementation method, the energy-saving modules in the energy-saving management system include an air-conditioning energy-saving management module, a wind-heat transfer energy-saving management module, a data center equipment energy-saving management module and a power distribution system energy-saving management module. The air-conditioning energy-saving management module is used to obtain the power consumption of the air conditioner in the data center. The wind-heat transfer energy-saving management module is used to obtain the sensor data of the temperature sensor and the humidity sensor in the data center. The data center equipment energy-saving management module is used to obtain the temperature of the processor in the data center and the load energy consumption data of the server in the data center. The power distribution system energy-saving management module is used to obtain the energy consumption data of the power distribution system in the data center.

[0019] As a possible implementation method, the method also includes: obtaining the computing power of the control unit responsible for controlling the target energy-saving module, and determining the working status of the electrical equipment based on the computing power change trend of the control unit and the energy consumption ratio change trend of the electrical equipment managed by the target energy-saving module.

[0020] In the above-mentioned implementation, not only the energy consumption ratio change trend of the target energy-saving module is paid attention to, but also the computing power change trend of the control unit responsible for controlling the energy-saving module is combined, so as to more comprehensively evaluate and optimize the working condition of the electrical equipment.

[0021] As a possible implementation method, the working condition of the power-consuming equipment is determined based on the changing trend of the computing power of the computing unit and the changing trend of the energy consumption ratio of the power-consuming equipment managed by the target energy-saving module, including: when the energy consumption ratio of the power-consuming equipment decreases as the computing power of the control unit increases, the control unit continues to execute the current control strategy.

[0022] As a possible implementation method, the working condition of the power-consuming equipment is determined based on the changing trend of the computing power of the computing unit and the changing trend of the energy consumption ratio of the power-consuming equipment managed by the target energy-saving module, including: when the energy consumption ratio of the power-consuming equipment does not decrease with the increase of the computing power of the control unit, the control unit changes the currently executed control strategy.

[0023] By combining the change trend of the computing power of the control unit and the change trend of the energy consumption ratio of the power-consuming equipment, the data center can more comprehensively evaluate and optimize the working conditions of the power-consuming equipment, thereby improving the level of refinement of energy management.

[0024] In a second aspect, the present application provides an energy-saving management system data analysis device, comprising:

[0025] The collection module is used to obtain the energy-saving data of each energy-saving module in the energy-saving management system of the data center, and the energy-saving data includes power consumption and power consumption;

[0026] A calculation module is used to compare the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module, and determine the change trend of the energy consumption ratio of the power-consuming equipment managed by each energy-saving module. The energy consumption ratio is the ratio of the power consumption value of the power-consuming equipment to the overall power consumption value of the data center;

[0027] A judgment module is used to judge whether a network attack occurs according to the change trend of the energy consumption ratio of the power-consuming equipment corresponding to each energy-saving module;

[0028] The evaluation module is used to evaluate the harmfulness of the network attack on the target energy-saving module when it is determined that the target energy-saving module has been attacked by a network. The target energy-saving module is any energy-saving module among the energy-saving modules.

[0029] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the energy-saving management system data analysis method of any one of the first aspects is implemented.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, any energy-saving management system data analysis method in the first aspect is implemented.

[0031] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, which is executed by a processor to implement any energy-saving management system data analysis method as described in the first aspect above.

[0032] The technical effects brought about by any one of the implementation methods in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of the steps of the energy-saving management system data processing method provided in this application;

[0034] Figure 2 It is a structural diagram of the energy-saving management system;

[0035] Figure 3A This is a schematic diagram of the energy consumption of the data center inspection in the previous period;

[0036] Figure 3B This is a schematic diagram of the energy consumption of the data center inspection during the current period;

[0037] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0038] Figure 5A schematic diagram of the structure of a data analysis device for an energy-saving management system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The specific operating method in the method embodiment can also be applied to the device embodiment or the system embodiment. It should be noted that in the description of the present application, "at least one" refers to one or more, wherein multiple refers to two or more. In view of this, "multiple" can also be understood as "at least two" in the embodiment of the present application. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the related objects before and after are in an "or" relationship. In addition, it should be understood that in the description of the present application, words such as "first" and "second" are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0040] Below, some of the terms involved in the embodiments of the present application are explained to facilitate easy understanding by those skilled in the art.

[0041] (1) Power Usage Effectiveness (PUE) is an important indicator for measuring the energy efficiency of a data center. It is defined as the ratio of the total energy consumption of a data center to the energy consumption of IT equipment. The closer the PUE value is to 1.0, the higher the energy efficiency of the data center, that is, the less energy is consumed by non-IT equipment (such as cooling systems, lighting, etc.).

[0042] (2) Forgery attack: If the user reuses a random value for different versions of data when generating digital labels, then in the storage node, the CSP may forge the data label of the data block to deceive the verifier.

[0043] (3) Substitution attack. Virus intrusion generally refers to hackers using the Internet to spread viruses and attack the network or game server. It also refers to implanting viruses into personal computers through technical means to steal user personal data, privacy information, and even bank account information, etc., in order to obtain improper benefits. When the data block m or label is lost, another legitimate data and data label may be used to replace the challenge pair sent by the verifier.

[0044] (4) Replay Attacks, also known as replay attacks or playback attacks, refer to an attacker sending a packet that has already been received by the destination host to deceive the system. It is mainly used in the identity authentication process to undermine the correctness of the authentication. Replay attacks can be carried out by the initiator or by the enemy who intercepts and resends the data. The attacker steals the authentication credentials through network monitoring or other means, and then resends it to the authentication server. Replay attacks can occur in any network communication process and are one of the common attack methods used by hackers in the computer world.

[0045] (5) Ransomware is a new type of computer virus that is mainly spread in the form of emails, program Trojans, and web page Trojans. The virus is of a bad nature and extremely harmful. Once infected, it will cause immeasurable losses to users. This virus uses various encryption algorithms to encrypt files. The infected person is generally unable to decrypt them. The decryption private key must be obtained to crack it.

[0046] (6) Dictionary data structure, which stores key-value pairs. Each key is unique and associated with a specific value. This data structure allows you to quickly find the corresponding value by key without traversing the entire data set.

[0047] With the rapid advancement of information technology, data centers, as important infrastructure behind modern services such as cloud computing and big data, are playing an increasingly critical role in today's society. However, as the scale of these facilities has expanded, the energy they consume has also increased significantly, which has become a major obstacle to the long-term sustainable development of data centers. Traditionally, energy management in data centers has focused on improving the efficiency of individual devices or systems, but lacks an overall grasp and analysis of the energy consumption of the entire facility, making it difficult to achieve optimal resource allocation and overall energy consumption optimization.

[0048] The main energy consumption of a data center during operation comes from the air conditioning system, wind heat management system, information technology (IT) equipment, and power distribution system. These components are not only related to the power efficiency index (PUE) of the data center, but are also crucial to maintaining the stability of the internal environment of the data center and ensuring the normal operation of IT equipment.

[0049] In order to effectively manage and optimize the energy consumption of data centers, it is necessary to be able to quickly collect and utilize energy-saving data involving the above-mentioned power-consuming devices. However, most current solutions adopt a post-processing approach, that is, first accumulating a large amount of raw data, and then storing and analyzing it offline. This approach is not suitable for application scenarios that require immediate response. At the same time, existing energy-saving measures are often only targeted at specific power-consuming units, and various types of power-consuming devices are not considered comprehensively under a unified framework, thus limiting the overall effectiveness of energy-saving strategies. In addition, in the face of increasingly severe network security threats, data centers are often the target of malicious attacks, but current energy-saving management systems usually do not have sufficient security protection functions to resist these potential risks.

[0050] In view of this, the present application provides a new energy-saving management system data analysis method, which can more effectively solve these problems, improve the energy utilization efficiency of the data center, and enhance its security.

[0051] See also Figure 1 As shown, Figure 1 This is a flow chart of the steps of the energy-saving management system data processing method provided by the present application, the method comprising the following steps:

[0052] Step S101, obtaining energy-saving data of each energy-saving module in the energy-saving management system of the data center, where the energy-saving data includes power consumption and power consumption.

[0053] See also Figure 2 As shown, Figure 2 The energy-saving management system of the data center of the present invention mainly includes the following modules: air conditioning energy-saving management module 201, wind heat transfer energy-saving management module 202, data center equipment energy-saving management module 203, power distribution system energy-saving management module 204. Each module is responsible for collecting energy consumption data of a specific energy-saving management system, and performing comprehensive analysis and optimization through the control unit of the data center.

[0054] The air conditioning energy saving management module 201 obtains the power consumption data of the air conditioning system in the current period through program inspection, and records and analyzes these energy saving data. Its main goal is to reduce the power consumption of the air conditioning in the data center, thereby effectively reducing the PUE value of the data center.

[0055] The air conditioning energy saving management module 201 collects the power consumption data of the air conditioning system regularly and records the relevant environmental conditions (such as temperature, humidity, etc.). Combined with historical data and real-time environmental conditions, the energy consumption pattern and efficiency of the air conditioning system are analyzed. According to the analysis results, the working mode of the air conditioning is dynamically adjusted. For example, the cooling mode is optimized, the set temperature is adjusted, the energy saving mode is enabled, etc. Exemplarily, by optimizing the working mode of the air conditioning system, the PUE value of the data center is reduced, thereby improving the energy utilization efficiency.

[0056] The wind heat energy saving management module 202 monitors the temperature and humidity in the data center through temperature and humidity sensors, and records the working status of related equipment such as chillers, humidifiers, lighting equipment, auxiliary equipment, etc. Its main function is to optimize the cooling effect of the data center and reduce unnecessary energy consumption.

[0057] Specifically, the wind heat energy saving management module 202 monitors the temperature and humidity in the data center in real time through temperature and humidity sensors, and records the working status of chillers, humidifiers, lighting equipment, auxiliary equipment, etc., and combines historical data and real-time monitoring data to analyze the cooling demand and equipment operation efficiency of the data center. The working mode of the cooling equipment is dynamically adjusted according to the sensor data to ensure that energy is saved to the maximum extent while meeting the cooling demand. For example, the outlet water temperature of the chiller is automatically adjusted, and the start and stop of the humidifier is controlled.

[0058] The data center equipment energy-saving management module 203 is used to obtain the processor temperature of IT equipment in the data center and the server load energy consumption data in the data center through program inspection, and to monitor and analyze these data in real time. Its function is to reduce the energy consumption of IT equipment and servers in the data center, especially to reduce the processor temperature of IT equipment and the load of servers, thereby reducing the PUE value of the data center. The specific implementation method is that the wind heat energy-saving management module 202 automatically adjusts the working status of IT equipment and servers based on real-time data and historical energy consumption trends, such as dynamically allocating computing resources, optimizing task scheduling, etc.

[0059] The power distribution system energy-saving management module 204 is used to obtain the energy consumption data of the power distribution system through program inspection and analyze it in combination with historical data. Its purpose is to reduce the energy consumption of the uninterruptible power supply (UPS) and the power distribution unit (PDU) and improve the overall efficiency of the power distribution system. The wind heat transfer energy-saving management module 202 optimizes the power distribution path and load distribution through intelligent algorithms, thereby reducing unnecessary power loss.

[0060] Through the comprehensive application of the above four modules, data centers can achieve more efficient energy management and optimization. Each module ensures that data centers can meet business needs while minimizing energy consumption and improving energy utilization efficiency through real-time data collection and intelligent adjustment, thereby reducing PUE values. This not only helps reduce operating costs, but also enables data centers to develop in a green and sustainable direction.

[0061] It should be noted that the energy-saving management system in the data center provided in this application may include but is not limited to the above-mentioned modules. Technical personnel in this field can add or reduce various energy-saving management modules according to the specific situation of the data center, and no further details will be given here.

[0062] For the above four modules (air conditioning energy saving management module 201, wind heat transfer energy saving management module 202, data center equipment energy saving management module 203 and power distribution system energy saving management module 204), the energy saving data may include multiple types. The following are the specific energy saving data that each module may collect:

[0063] The specific energy-saving data of the air-conditioning energy-saving management module 201 may include: the power consumption of the air-conditioning system in the current period, the power consumption of the air-conditioning system. Example energy-saving data may be: the power consumption of the air-conditioning system is 140 kWh, and the power consumption is 30 kW.

[0064] The specific energy-saving data of the wind heat energy-saving management module 202 may include: the power consumption of the chiller in the current period, the power consumption of the chiller, the power consumption of the cooling fan, the power consumption of the cooling fan, the power consumption of the water pump, and the power consumption of the water pump. Example energy-saving data may be: the power consumption of the chiller is 50 kWh and the power consumption is 5 kW.

[0065] The specific energy-saving data of the data center equipment energy-saving management module 203 may include: real-time power consumption of IT equipment and servers, power consumption of IT equipment and servers, and an example of energy-saving data may be: the power consumption of server B is 300W.

[0066] The specific energy-saving data of the power distribution system energy-saving management module 204 may include: real-time power consumption of the power distribution system, power consumption of the power distribution system, power consumption of the uninterruptible power supply, power consumption of the uninterruptible power supply, power consumption of the equipment connected to each interface of the power distribution unit, and power consumption of the equipment connected to each interface of the power distribution unit. Example energy-saving data may be: the total power consumption of the power distribution system is 400KVA, the power consumption of the uninterruptible power supply is a specific value, the power consumption of the equipment connected to interface 1 of the power distribution unit is 100W, and the power consumption of the equipment connected to interface 2 is 200W.

[0067] Step S102, compare the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module to determine the energy consumption ratio change trend of the power-consuming equipment managed by each energy-saving module. The energy consumption ratio is the ratio of the power consumption value of the power-consuming equipment to the overall power consumption value of the data center.

[0068] Specifically, the power consumption and power consumption of each energy-saving module (such as air conditioning system, wind-shift thermal management system, IT equipment and server, power distribution system, etc.) are monitored and recorded in real time, and the power consumption and power consumption records of the same module in the past period of time are extracted from the database. By comparing and analyzing the current data with the historical data, the energy consumption ratio changes of each module are calculated.

[0069] The above description may include: calculating the proportion of the power consumption of each module in the current period to the total power consumption of the data center, comparing the proportion with the historical data of the same period or the previous period, and determining whether it is increasing or decreasing. Based on the above comparison results, the trend of the energy consumption ratio of each module over time can be obtained. For example, if the energy consumption ratio of a module is found to continue to increase, it may mean that the module has a problem of reduced efficiency. On the contrary, if the energy consumption ratio decreases, it means that the energy efficiency has improved.

[0070] By regularly comparing energy-saving data, abnormally high power consumption can be quickly identified, so that measures can be taken to reduce unnecessary energy waste. In addition, understanding the energy consumption distribution between different modules helps to reasonably adjust resource usage, ensuring that critical businesses are supported by sufficient power while maximizing energy savings.

[0071] Long-term tracking of energy consumption ratio trends is conducive to formulating more effective energy-saving strategies, such as improving cooling technology, upgrading hardware facilities, or adjusting operating modes, ultimately reducing the PUE of the data center and significantly reducing operating costs.

[0072] For example, the cooling in the data center is mainly provided by the data center air conditioner. Reducing the power consumption of the data center air conditioner can effectively reduce the PUE value of the data center. The data of the previous period (for example, the previous hour) has been recorded in the historical database, and the data of the current period (this hour) is obtained through program inspection.

[0073] Data from the previous period: Power consumed by air conditioners: 1.6kWh, air conditioners account for 15% of the total energy consumption of the data center; data from the current period: Power consumed by air conditioners: 1.28kWh.

[0074] The increase / decrease ratio = (power consumption in this period - power consumption in the previous period) / power consumption in the previous period. Therefore, the increase / decrease ratio = (1.28kWh - 1.6kWh) / 1.6kWh = -0.32 / 1.6 = -20%, which means that the energy consumption is reduced by 20%.

[0075] In the previous period, air conditioning accounted for 15% of the total energy consumption of the data center, and in this period, air conditioning accounted for 12% of the total energy consumption of the data center. Therefore, in the previous period, the air conditioning system consumed 1.6kWh, accounting for 15% of the total energy consumption of the data center. In this period, the air conditioning system consumed 1.28kWh, which was 20% lower than the previous period. The energy consumption of the air conditioning system in the current period has dropped from 15% to 12%.

[0076] As a possible implementation method, the energy-saving data of each energy-saving module is compared with the historical energy-saving data of each energy-saving module to determine the energy consumption ratio change trend of the power-consuming equipment managed by each energy-saving module, specifically including:

[0077] At least one historical energy-saving data of each energy-saving module and the currently acquired energy-saving data are taken as a data set, and the average value of the energy-saving data in the data set is taken as the set data threshold. According to the number of energy-saving data above and below the set data threshold in the data set, the energy consumption ratio change trend of the electrical equipment corresponding to each energy-saving module is determined.

[0078] The currently acquired energy-saving data is merged with at least one historical energy-saving data to form a data set containing multiple groups of data. The average value of all energy-saving data in the data set is calculated, and this average value is used as the set data threshold. According to the number of energy-saving data in the data set that is higher than and lower than the set data threshold, the change trend of the energy consumption ratio of the power-consuming equipment corresponding to each energy-saving module is determined. If the number of data higher than the set data threshold is large, it means that the energy consumption ratio of the power-consuming equipment managed by the energy-saving module may be increasing. If the number of data lower than the set data threshold is large, it means that the energy consumption ratio of the power-consuming equipment managed by the energy-saving module may be decreasing.

[0079] By comparing the current data with the average of historical data, we can find out which modules have significant changes in energy consumption, which helps to take measures to deal with potential problems. Based on detailed energy consumption data analysis, we can more accurately understand the performance of each energy-saving module, so as to carry out more refined energy management and optimization. By continuously tracking the trend of energy consumption ratio changes, we can help predict future energy consumption, thereby providing a basis for formulating long-term energy-saving strategies. After obtaining the trend of energy consumption ratio changes, we can adjust the operating parameters or update the hardware of energy-saving equipment according to the specific situation to achieve a higher energy efficiency level and reduce the PUE value of the data center.

[0080] Exemplarily, the historical air-conditioning power consumption in the last nine time periods plus the current air-conditioning power consumption can be obtained to form a data set of ten times, and the average value of all energy-saving data in the data set can be calculated. This average value is used as the set data threshold, and the changing trend of the energy consumption ratio of the air-conditioning system can be judged by counting the number of energy-saving data that are higher and lower than the set data threshold.

[0081] Assume that the air conditioning power consumption (unit: kWh) in the last 9 time periods are: 1.5, 1.6, 1.7, 1.8, 1.9, 2.0, 2.1, 2.2, 2.3, and the air conditioning power consumption in the current period is: 1.4kWh, data set = [1.5, 1.6, 1.7, 1.8, 1.9, 2.0, 2.1, 2.2, 2.3, 1.4], the calculated average value = (1.5+1.6+1.7+1.8+1.9+2.0+2.1+2.2+2.3+1.4) / 10 = 1.85kWh, so the set data threshold is 1.85kWh.

[0082] Count the number of times above and below the set data threshold: data above the threshold: [1.9, 2.0, 2.1, 2.2, 2.3], data below the threshold: [1.5, 1.6, 1.7, 1.8, 1.4]. In this example, the number of data above and below the threshold is the same, both 5 times. Therefore, the probability of the next energy consumption ratio trend being normal is 50%, and the probability of being abnormal is 50%.

[0083] It should be noted that there is no limit to the number of energy-saving data in the data set, and those skilled in the art can freely set it, which is not limited here.

[0084] See also Figure 3A As shown, Figure 3A This is a schematic diagram of the energy consumption of the data center inspection in the previous period. IT equipment accounts for 47%, which is the largest source of energy consumption. Air conditioning accounts for 15%, humidifiers account for 3%, chillers account for 24%, PDU accounts for 3%, UPS accounts for 6%, lighting and auxiliary equipment accounts for 2%, and switch devices or generators account for 1%. All of the above equipment are installed to maintain a stable internal environment in the data center.

[0085] See also Figure 3B As shown, Figure 3B This is a schematic diagram of the energy consumption of the data center inspection in the current period. IT equipment accounts for 42.3%, air conditioning accounts for 12%, and chillers account for 19.2%. In addition, there are other equipment such as PDU accounts for 2%, UPS accounts for 3%, lighting and auxiliary equipment accounts for 2%, and switchgear / generators account for 1%.

[0086] From the previous period to the current period, the energy consumption of major energy consumption sources such as IT equipment and air conditioning equipment has decreased.

[0087] Step S103, judging whether a network attack occurs according to the change trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module.

[0088] Among them, when it is determined that the change trend of the energy consumption ratio of the electrical equipment corresponding to the target energy-saving module deviates from the set change range, the energy-saving data of the target energy-saving module is input into the network attack judgment model. The network attack judgment model is trained based on the energy-saving data of the energy-saving module that is attacked by the network. The network attack judgment model is used to extract feature information related to the network attack in the energy-saving data of the target energy-saving module, and determine the type of network attack suffered by the target energy-saving module based on the feature information related to the network attack.

[0089] When it is determined that the energy consumption ratio change trend of a target energy-saving module (such as an air-conditioning system, wind-shift thermal management system, etc.) deviates from the set change range, the energy-saving data of the energy-saving module can be input into a pre-trained network attack judgment model. This model is trained based on the historical energy-saving data of energy-saving modules that have been attacked by the network, and can extract feature information related to the network attack, and determine whether the target energy-saving module has been attacked by the network and the specific type of attack based on this feature information.

[0090] Specifically, the current energy-saving data (such as power consumption, power consumption, etc.) of the target energy-saving module is collected, and historical energy-saving data, especially those data known to be subject to network attacks, are collected. The historical energy-saving data known to be subject to network attacks is used to train the network attack judgment model. During the training process, the model can be trained to learn and obtain feature information related to network attacks, such as abnormal energy consumption patterns, abnormal operating behaviors, etc. The current energy-saving data of the target energy-saving module is input into the trained network attack judgment model, and the network attack judgment model extracts feature information related to network attacks from the input data. These features may include, but are not limited to: sudden surges or drops in energy consumption, etc. Based on the extracted feature information, the network attack judgment model determines whether the target energy-saving module has been attacked by a network.

[0091] By real-time monitoring and analysis of energy-saving data, potential network attacks can be discovered in a timely manner, so that countermeasures can be taken quickly to reduce losses, better protect energy-saving management equipment and electrical equipment from network attacks, and improve overall security.

[0092] As a possible implementation method, at least one type of network attack type includes: a forged attack type, a substitution attack type, a replay attack type, and a ransomware attack type.

[0093] The network attack judgment model extracts characteristic information related to network attacks from the input data. For example: Forgery attack: abnormal authentication request, mismatched IP address, etc. Substitution attack: data integrity check failure, data checksum inconsistency, etc. Replay attack: duplicate data packets, abnormal timestamp, duplicate serial number, etc. Ransomware attack: abnormal file encryption activity, a large number of files are locked, etc.

[0094] By inputting energy-saving data into a network attack judgment model trained based on historical data of network attacks, data centers can effectively detect and classify network attacks, thereby improving the security of the system and helping data centers to promptly detect and respond to potential security threats.

[0095] As a possible implementation method, the network attack judgment model is used to extract characteristic information related to network attacks in the energy-saving data of the target energy-saving module, specifically including: converting the characteristic information related to network attacks in the energy-saving data of the target energy-saving module into dictionary structure data, and the network attack judgment model outputs the network attack type in text form based on the dictionary structure data.

[0096] In the above possible implementation, the network attack judgment model is used to extract the characteristic information related to the network attack in the energy-saving data of the target energy-saving module, and convert the characteristic information into data in a dictionary structure. Then, based on the data in the dictionary structure, the model outputs the network attack type in text form. The specific steps are as follows:

[0097] Extract characteristic information related to network attacks from the energy-saving data of the target energy-saving module. These characteristic information may include abnormal energy consumption patterns, unusual operation behaviors, abnormal authentication requests, etc.

[0098] The extracted feature information is organized into dictionary-structured data. The key-value pairs in the dictionary can contain various relevant information, such as energy consumption, power consumption, timestamp, etc. The network attack judgment model analyzes the above dictionary structure data and outputs the network attack type in text form. For example, the model may output "forgery attack detected" or "replay attack detected".

[0099] To guide a large language model, extract key information and convert it into a dictionary structure, the following steps are included:

[0100] First, extract abnormal feature information related to network attacks from energy-saving data. Then, organize this key information into dictionary-structured data. Use a large language model to obtain all relevant associated data. The large language model can provide contextual information and associated data based on the input keywords without the need to manually query log files.

[0101] Based on the relevant data obtained from the large language model, a dictionary data structure containing detailed information is built to make the data more structured and easier to process.

[0102] By basing the model on relevant dictionary data rather than large-scale inspection data, the risk of large language models generating erroneous or irrelevant content can be reduced, which helps improve the accuracy of generated text. In addition, large language models can better understand the context and provide more precise results. Compared with directly querying and associating data from raw logs, the process of extracting corresponding data values ​​is simpler and more efficient, reducing the complexity and time cost of data processing.

[0103] In addition, the data in the dictionary structure is more intuitive, easy to process and understand, and convenient for subsequent analysis and decision-making. This method makes data management more orderly and reduces the size of the constructed dictionary, thereby reducing the time required to analyze the text and improving efficiency.

[0104] By converting the cyber attack feature information in energy-saving data into dictionary structured data and using large language models for processing and analysis, data centers can more effectively detect and classify cyber attacks, which not only improves the accuracy and efficiency of detection but also simplifies the data processing process.

[0105] Step S104, when it is determined that a network attack occurs on a target energy-saving module, a hazard assessment is performed on the network attack on the target energy-saving module, where the target energy-saving module is any energy-saving module among the energy-saving modules.

[0106] When it is determined that a network attack has occurred on the target energy-saving module, a hazard assessment is performed on the network attack. The specific steps are as follows:

[0107] The network attack judgment model is used to determine the types of network attacks that the target energy-saving module is subjected to. These attack types may include counterfeit attacks, substitution attacks, replay attacks, and ransomware attacks.

[0108] According to the risk assessment model, the potential risk level of each type of network attack is determined, wherein the risk assessment model is constructed based on historical data and statistical learning methods to evaluate the potential risks of different types of network attacks.

[0109] For example, certain attack types (such as ransomware) may be marked as high risk, while other attack types (such as simple forgery attacks) may be marked as medium risk or low risk.

[0110] The determined potential risk level is marked on the energy-saving data of the target energy-saving module, so that it is intuitive to see which data is affected by which level of network attack.

[0111] Using energy-saving data with potential risk level labels to update and train the network attack judgment model helps the model continuously learn new attack patterns and improve its ability to identify and classify network attacks. Evaluate and compare the output text answers to obtain results with quality scores or risk levels to help verify the accuracy and reliability of the model.

[0112] By using a risk assessment model, the potential risk level of different cyber attack types can be more accurately assessed, helping data center managers better understand the impact of an attack.

[0113] Using data with potential risk level markers to update and train the network attack judgment model, the model can continuously adapt to new attack patterns and improve its recognition and classification capabilities. Based on the risk level markers, the data center can prioritize high-risk attack events, reasonably allocate management resources, improve overall security protection efficiency, and output text-based answers with quality scores or risk levels to adapt to ever-changing network attacks.

[0114] As a possible implementation method, the method provided in the present application also includes: obtaining the computing power of the control unit responsible for controlling the target energy-saving module, and determining the working status of the electrical equipment based on the computing power change trend of the control unit and the energy consumption ratio change trend of the electrical equipment managed by the target energy-saving module.

[0115] In the above-mentioned implementation, not only the energy consumption ratio change trend of the target energy-saving module is paid attention to, but also the computing power change trend of the control unit responsible for controlling the energy-saving module is combined, so as to more comprehensively evaluate and optimize the working condition of the electrical equipment.

[0116] The computing power here can refer to the computing power, processing speed or other performance indicators of the control unit. Analyze the computing power change trend of the control unit, including the change of computing power over time, such as whether the computing power is increasing, decreasing or remaining stable. Analyze the energy consumption ratio change trend of the power-consuming equipment managed by the target energy-saving module. According to the computing power change trend of the control unit and the energy consumption ratio change trend of the power-consuming equipment, comprehensively judge the working condition of the power-consuming equipment and decide whether the control strategy needs to be adjusted.

[0117] Specifically, there are two situations: When the energy consumption ratio of the power-consuming equipment decreases as the computing power of the control unit increases:

[0118] If it is observed that when the computing power of the control unit increases, the energy consumption ratio of the power-consuming equipment also decreases, it means that the current control strategy is effective. At this time, the control unit can continue to execute the current control strategy, and using this strategy helps improve energy efficiency.

[0119] When the energy consumption ratio of the power-consuming equipment does not decrease as the computing power of the control unit increases:

[0120] If it is observed that the energy consumption ratio of the power-consuming equipment does not decrease accordingly or even increases when the computing power of the control unit increases, it means that the current control strategy may have problems or is no longer effective. At this time, the control unit needs to change the currently executed control strategy to find a better control method to reduce the energy consumption ratio.

[0121] By combining the change trend of the computing power of the control unit and the change trend of the energy consumption ratio of the power-consuming equipment, the data center can more comprehensively evaluate and optimize the working conditions of the power-consuming equipment, which not only improves the level of refinement of energy management, but also helps to reduce costs and improve reliability.

[0122] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0123] The electronic device includes at least one processor 401 and a memory 402 connected to the at least one processor 401. The specific connection medium between the processor 401 and the memory 402 is not limited in the embodiment of the present application. Figure 4 In the example, the processor 401 and the memory 402 are connected via the bus 403. The bus 403 is Figure 4 The connection between other components is shown by bold lines, and is not intended to be limiting. The bus 403 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 401 can also be called a controller, and there is no limitation on the name.

[0124] In an embodiment of the present application, the memory 402 stores instructions that can be executed by at least one processor 401. By executing the instructions stored in the memory 402, at least one processor 401 can execute an energy-saving management system data processing method described in the above embodiment.

[0125] Among them, the processor 401 is the control center of the device, and can use various interfaces and lines to connect the various parts of the entire control device. By running or executing instructions stored in the memory 402 and calling the data stored in the memory 402, the various functions of the device and process data, the device can be monitored as a whole.

[0126] In one possible design, the processor 401 may include one or more processing units, and the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a driver interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 401. In some embodiments, the processor 401 and the memory 402 may be implemented on the same chip, and in some embodiments, they may also be implemented separately on separate chips.

[0127] Processor 401 can be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of a model acquisition method disclosed in the embodiments of the present application can be directly embodied as a hardware processor execution, or a combination of hardware and software modules in the processor.

[0128] The memory 402 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 402 may include at least one type of storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory, a random access memory (Random Access Memory, RAM), a static random access memory (Static Random Access Memory, SRAM), a programmable read-only memory (Programmable Read Only Memory, PROM), a read-only memory (Read Only Memory, ROM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), a magnetic memory, a disk, an optical disk, etc. The memory 402 is any other medium that can be used to carry or store a desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 402 in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0129] By programming the processor 401, the code corresponding to the model acquisition method described in the above embodiment can be fixed into the chip, so that the chip can execute the code when running. Figure 1The embodiment shown is a data analysis method for an energy-saving management system. How to design and program the processor 401 is a technology well known to those skilled in the art and will not be described in detail here.

[0130] It should be noted here that the above-mentioned electronic device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0131] Figure 5 A schematic diagram of the structure of the energy-saving management system data analysis device provided in the embodiment of the present application, such as Figure 5 As shown, the device includes: a collection module 501, a calculation module 502, a judgment module 503, and an evaluation module.

[0132] The acquisition module 501 is used to obtain energy-saving data of each energy-saving module in the energy-saving management system of the data center, and the energy-saving data includes power consumption and power consumption;

[0133] The calculation module 502 is used to compare the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module to determine the change trend of the energy consumption ratio of the power-consuming equipment managed by each energy-saving module, where the energy consumption ratio is the ratio of the power consumption value of the power-consuming equipment to the overall power consumption value of the data center;

[0134] The judgment module 503 is used to judge whether a network attack occurs according to the change trend of the energy consumption ratio of the electric equipment corresponding to each energy-saving module;

[0135] The evaluation module 504 is used to evaluate the harmfulness of the network attack on the target energy-saving module when it is determined that the target energy-saving module has been attacked by a network. The target energy-saving module is any energy-saving module among the energy-saving modules.

[0136] Optionally, the calculation module 502 is used to compare the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module to determine the change trend of the energy consumption ratio of the electrical equipment managed by each energy-saving module, specifically including: taking at least one historical energy-saving data of each energy-saving module and the currently acquired energy-saving data as a data set, taking the average value of the energy-saving data in the data set as a set data threshold, and determining the change trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module according to the number of energy-saving data above and below the set data threshold in the data set.

[0137] Optionally, the judgment module 503 is specifically used to judge whether a network attack has occurred based on the changing trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module, specifically including: when it is determined that the changing trend of the energy consumption ratio of the electrical equipment corresponding to the target energy-saving module deviates from the set changing range, the energy-saving data of the target energy-saving module is input into the network attack judgment model, the network attack judgment model is trained based on the energy-saving data of the energy-saving module that is attacked by the network, and the network attack judgment model is used to extract feature information related to the network attack from the energy-saving data of the target energy-saving module, and determine the type of network attack suffered by the target energy-saving module based on the feature information related to the network attack.

[0138] Optionally, at least one type of network attack includes: a forged attack type, a substitution attack type, a replay attack type, and a ransomware attack type.

[0139] Optionally, the judgment module 503 is specifically used to convert feature information related to network attacks in the energy-saving data of the target energy-saving module into dictionary structure data, and the network attack judgment model outputs the network attack type in text form based on the dictionary structure data.

[0140] Optionally, the evaluation module 504 is specifically used to determine the potential risk level corresponding to the network attack type suffered by the target energy-saving module according to the risk evaluation model, wherein the risk evaluation model is used to evaluate the potential risk level of each network attack type, mark the potential risk level on the energy-saving data of the target energy-saving module, and use the energy-saving data with the potential risk level mark to update and train the network attack judgment model. Perform evaluation and comparison on the answers in text form to obtain results with quality scores or risk levels.

[0141] Optionally, the calculation module 502 is also used to obtain the computing power of the control unit responsible for controlling the target energy-saving module, and determine the working status of the electrical equipment according to the computing power change trend of the control unit and the energy consumption ratio change trend of the electrical equipment managed by the target energy-saving module.

[0142] Optionally, the calculation module 502 is also used for the control unit to continue to execute the current control strategy when the energy consumption ratio of the electrical equipment decreases as the computing power of the control unit increases.

[0143] Optionally, the calculation module 502 changes the currently executed control strategy when the energy consumption ratio of the electrical equipment does not decrease as the computing power of the control unit increases.

[0144] An embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute an energy-saving management system data analysis method in the above embodiment.

[0145] An embodiment of the present application also provides a computer program product. When the computer program product is called by a computer, it enables the computer to execute an energy-saving management system data analysis method in the above embodiment.

[0146] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may 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 may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0147] 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 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 processor, 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.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A data analysis method for energy-saving management system, applied to a data center, characterized in that: The method comprises: Acquire energy-saving data of each energy-saving module in the energy-saving management system of the data center, wherein the energy-saving data includes power consumption and power consumption; Compare the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module to determine the change trend of the energy consumption ratio of the power-consuming equipment managed by each energy-saving module, where the energy consumption ratio is the ratio of the power consumption value of the power-consuming equipment to the overall power consumption value of the data center; Determine whether a network attack occurs according to the change trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module; When it is determined that the network attack occurs on a target energy-saving module, a harmfulness assessment is performed on the network attack occurring on the target energy-saving module, wherein the target energy-saving module is any energy-saving module among the energy-saving modules.

2. The method according to claim 1, characterized in that Comparing the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module to determine the energy consumption ratio change trend of the power-consuming equipment managed by each energy-saving module specifically includes: Taking at least one historical energy-saving data of each energy-saving module and the currently acquired energy-saving data as a data set, and taking the average value of the energy-saving data in the data set as a set data threshold; According to the number of energy-saving data in the data set that is higher than and lower than the set data threshold, the change trend of the energy consumption ratio of the electric equipment corresponding to each energy-saving module is determined.

3. The method according to claim 2, characterized in that According to the energy consumption ratio change trend of the electric equipment corresponding to each energy-saving module, it is judged whether a network attack occurs, specifically including: When it is determined that the change trend of the energy consumption ratio of the electric equipment corresponding to the target energy-saving module deviates from the set change interval, the energy-saving data of the target energy-saving module is input into a network attack judgment model, wherein the network attack judgment model is trained based on the energy-saving data of the energy-saving module under network attack; The network attack judgment model is used to extract characteristic information related to network attacks from the energy-saving data of the target energy-saving module; The type of network attack suffered by the target energy-saving module is determined according to the characteristic information related to the network attack.

4. The method according to claim 3, characterized in that The at least one type of network attack type includes: a forged attack type, a substitution attack type, a replay attack type, and a ransomware attack type.

5. The method according to claim 3, characterized in that: The network attack judgment model is used to extract characteristic information related to network attacks from the energy-saving data of the target energy-saving module, and specifically includes: Converting characteristic information related to network attacks in the energy-saving data of the target energy-saving module into dictionary structure data; The network attack judgment model outputs the network attack type in text form based on the dictionary structure data.

6. The method according to claim 3, characterized in that When determining that the target energy-saving module has been attacked by the network, performing a harmfulness assessment on the network attack on the target energy-saving module specifically includes: Determine the potential risk level corresponding to the type of network attack to which the target energy-saving module is subjected according to the risk assessment model, wherein the risk assessment model is used to evaluate the potential risk level of each type of network attack; Marking the potential risk level on the energy-saving data of the target energy-saving module; Using the energy-saving data with the potential risk level mark to update and train the network attack judgment model; An evaluation comparison is performed on the textual answers to obtain a result with a quality score or risk level.

7. The method according to any one of claims 1 to 6, characterized in that: The energy-saving modules in the energy-saving management system include an air-conditioning energy-saving management module, a wind heat transfer energy-saving management module, a data center equipment energy-saving management module, and a power distribution system energy-saving management module; The air conditioning energy saving management module is used to obtain the power consumption of the air conditioning of the data center; The wind heat transfer energy saving management module is used to obtain the sensing data of the temperature sensor and the humidity sensor in the data center; The data center equipment energy-saving management module is used to obtain the temperature of the processor in the data center and the load energy consumption data of the server in the data center; The power distribution system energy-saving management module is used to obtain energy consumption data of the power distribution system in the data center.

8. The method according to claim 7, characterized in that The method further comprises: Acquiring the computing power of the control unit responsible for controlling the target energy-saving module; The working status of the electric equipment is determined according to the change trend of the computing power of the control unit and the change trend of the energy consumption ratio of the electric equipment managed by the target energy-saving module.

9. The method according to claim 8, characterized in that Determining the working status of the electric device according to the change trend of the computing power of the computing unit and the change trend of the energy consumption ratio of the electric device managed by the target energy-saving module includes: When the energy consumption ratio of the electrical equipment decreases as the computing power of the control unit increases, the control unit continues to execute the current control strategy.

10. The method according to claim 8, characterized in that Determining the working status of the electric device according to the change trend of the computing power of the computing unit and the change trend of the energy consumption ratio of the electric device managed by the target energy-saving module includes: When the energy consumption ratio of the electric equipment does not decrease as the computing power of the control unit increases, the control unit changes the currently executed control strategy.

11. A data analysis device for an energy-saving management system, characterized in that: include: A collection module, used to obtain energy-saving data of each energy-saving module in the energy-saving management system of the data center, wherein the energy-saving data includes power consumption and power consumption; A calculation module, used for comparing the energy-saving data of each energy-saving module with the historical energy-saving data of each energy-saving module, and determining the change trend of the energy consumption ratio of the power-consuming equipment managed by each energy-saving module, wherein the energy consumption ratio is the ratio of the power consumption value of the power-consuming equipment to the overall power consumption value of the data center; A judgment module, used to judge whether a network attack occurs according to the change trend of the energy consumption ratio of the electrical equipment corresponding to each energy-saving module; The evaluation module is used to evaluate the harmfulness of the network attack occurring on the target energy-saving module when it is determined that the network attack occurs on the target energy-saving module, and the target energy-saving module is any energy-saving module among the energy-saving modules.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to cause the computer to execute the method according to any one of claims 1 to 10.

Images