CN115327264B - Abnormality detection method and device for data center, electronic equipment and medium - Google Patents
Abnormality detection method and device for data center, electronic equipment and medium Download PDFInfo
- Publication number
- CN115327264B CN115327264B CN202210901169.9A CN202210901169A CN115327264B CN 115327264 B CN115327264 B CN 115327264B CN 202210901169 A CN202210901169 A CN 202210901169A CN 115327264 B CN115327264 B CN 115327264B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- time period
- electric equipment
- electric
- transition probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
本发明实施例提供了一种数据中心的异常检测方法、装置、电子设备和介质，该方法包括：获取针对各用电设备所采集的目标能耗信息；然后，根据目标能耗信息，预测各用电设备在预设时间段的能耗升降情况；在预设时间段时，若接收到针对数据中心的能耗异常告警信息，则根据能耗升降情况，从多个用电设备中确定异常用电设备。通过本发明实施例，实现了预先针对数据中心的用电设备的能耗升降情况进行预测，当数据中心在预设时间段出现能耗异常时，可以基于预先得到的能耗升降情况快速的确定异常用电设备，从而提高了数据中心能耗异常时定位异常用电设备的效率，且无需逐个排查，节约了人力和物力资源。
The embodiments of the present invention provide a method, device, electronic device and medium for detecting anomalies in a data center. The method includes: obtaining target energy consumption information collected for each electrical device; then, based on the target energy consumption information, predicting the energy consumption increase and decrease of each electrical device in a preset time period; in the preset time period, if an abnormal energy consumption alarm information for the data center is received, then determining the abnormal electrical device from multiple electrical devices based on the energy consumption increase and decrease. Through the embodiments of the present invention, it is possible to predict the energy consumption increase and decrease of the electrical devices in the data center in advance. When the data center has abnormal energy consumption in the preset time period, the abnormal electrical devices can be quickly determined based on the energy consumption increase and decrease conditions obtained in advance, thereby improving the efficiency of locating abnormal electrical devices when the energy consumption of the data center is abnormal, and there is no need to check them one by one, saving manpower and material resources.
Description
Technical Field
The present invention relates to the field of anomaly detection technologies, and in particular, to a method, an apparatus, an electronic device, and a medium for anomaly detection in a data center.
Background
The data center may refer to a building site where electronic information devices are centrally located to provide an operating environment, in which various electrical devices may be deployed, such as air conditioning, IT (Internet Technology ) devices, lighting devices, and the like.
With the continuous development of computer technology, the services provided by the data center are more and more, the energy consumption of the data center is correspondingly larger, and in order to reduce the energy consumption of the data center, an energy consumption energy-saving system can be deployed in the data center to accurately control the electric equipment of the data center, so that the energy consumption of each electric equipment is reduced.
In practical applications, the power consumption of each electric device may be abnormal for various reasons, such as sudden increase/decrease of power consumption, and in the prior art, only the total power consumption or the local power consumption of the data center can be detected.
When detecting that the total energy consumption or the local energy consumption of the data center is abnormal, each device needs to be checked to determine which electric equipment has the abnormal energy consumption, and then the device with the abnormal energy consumption is overhauled.
However, the detection mode of the abnormal energy consumption is low in efficiency and needs to consume a great deal of manpower and material resources.
Disclosure of Invention
In view of the foregoing, there is provided a method, apparatus, electronic device, and medium for detecting anomalies in a data center that overcomes or at least partially solves the foregoing problems, including:
An anomaly detection method for a data center, in which a plurality of electric devices are deployed, the method comprising:
Acquiring target energy consumption information acquired for each electric equipment;
According to the target energy consumption information, predicting the energy consumption lifting condition of each electric equipment in a preset time period;
and when the preset time period is reached, if the energy consumption abnormality warning information aiming at the data center is received, determining abnormal electric equipment from the plurality of electric equipment according to the energy consumption lifting condition.
Optionally, the target energy consumption information includes current energy consumption information and historical energy consumption information, and predicting the energy consumption lifting condition of each electric device in a preset time period according to the target energy consumption information includes:
Determining first energy consumption transition probabilities of the plurality of electric devices in the previous time period and second energy consumption transition probabilities of the plurality of electric devices in the current time period according to the historical energy consumption information and the current energy consumption information;
Determining a third energy consumption transition probability of the plurality of electric devices in a preset time period according to the first energy consumption transition probability and the second energy consumption transition probability;
And predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the third energy consumption transition probability.
Optionally, the determining, according to the third energy consumption transition probability, an energy consumption lifting condition of each electric device in a preset time period includes:
determining the first electric quantity of each electric equipment in the current time period according to the current energy consumption information;
predicting a second electricity consumption of each electric equipment in a preset time period according to the third energy consumption transition probability and the first electricity quantity;
And predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the first electric quantity and the second electric quantity.
Optionally, the data center includes a plurality of areas, and determining, according to the energy consumption lifting condition, an abnormal electric device from the plurality of electric devices includes:
Determining an abnormality occurrence area from the plurality of areas according to the energy consumption abnormality warning information;
And determining abnormal electric equipment from the electric equipment in the abnormal occurrence area according to the energy consumption lifting condition.
Optionally, the energy consumption up-down condition includes an energy consumption up-down ratio or an energy consumption down ratio, and the method further includes:
when the energy consumption increasing proportion exceeds a first threshold value, carrying out abnormal alarm prompt on electric equipment corresponding to the energy consumption increasing proportion;
Or when the energy consumption reduction ratio exceeds a second threshold, carrying out abnormal alarm prompt on the electric equipment corresponding to the energy consumption reduction ratio.
The embodiment of the invention also provides an abnormality detection device of the data center, wherein a plurality of electric equipment is deployed in the data center, and the device comprises:
The acquisition module is used for acquiring target energy consumption information acquired for each electric equipment;
the prediction module is used for predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the target energy consumption information;
and the alarm module is used for determining abnormal electric equipment from the plurality of electric equipment according to the energy consumption lifting condition if the energy consumption abnormal alarm information aiming at the data center is received in a preset time period.
Optionally, the target energy consumption information includes current energy consumption information and historical energy consumption information, and the prediction module includes:
The first energy consumption probability determining submodule is used for determining first energy consumption transition probabilities of the plurality of electric equipment in the previous time period and second energy consumption transition probabilities of the plurality of electric equipment in the current time period according to the historical energy consumption information and the current energy consumption information;
A second energy consumption transition probability determination submodule, configured to determine a third energy consumption transition probability of the plurality of electric devices in a preset time period according to the first energy consumption transition probability and the second energy consumption transition probability;
And the lifting condition determining sub-module is used for predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the third energy consumption transition probability.
Optionally, the lifting condition determining submodule is used for determining first electric quantity of each electric equipment in a current time period according to the current energy consumption information, determining second electric quantity of each electric equipment in a preset time period according to the third energy consumption transition probability and the first electric quantity, and determining energy consumption lifting condition of each electric equipment in the preset time period according to the first electric quantity and the second electric quantity.
Optionally, the data center includes a plurality of areas, and the alarm module includes:
The region determination submodule is used for determining an abnormal occurrence region from the multiple regions according to the energy consumption abnormal alarm information;
And the abnormal equipment determining submodule is used for determining abnormal electric equipment from the electric equipment in the abnormal occurrence area according to the energy consumption lifting condition.
Optionally, the energy consumption lifting condition includes an energy consumption lifting proportion or an energy consumption reducing proportion, and the device further includes:
The first prompting module is used for prompting abnormal alarm aiming at electric equipment corresponding to the energy consumption increasing proportion when the energy consumption increasing proportion exceeds a first threshold value;
And the second prompting module is used for prompting abnormal alarm aiming at the electric equipment corresponding to the energy consumption reduction ratio when the energy consumption reduction ratio exceeds a second threshold value.
The embodiment of the invention also provides electronic equipment, which comprises a processor, a memory and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the abnormality detection method of the data center when being executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the abnormality detection method of the data center when being executed by a processor.
The embodiment of the invention has the following advantages:
In the embodiment of the invention, the target energy consumption information acquired for each electric equipment can be acquired first, then the energy consumption rising and falling condition of each electric equipment in a preset time period is predicted according to the target energy consumption information, and when the energy consumption abnormality warning information for the data center is received in the preset time period, the abnormal electric equipment is determined from the plurality of electric equipment according to the energy consumption rising and falling condition. According to the embodiment of the invention, the prediction of the energy consumption lifting situation of the electric equipment of the data center is realized, when the energy consumption of the data center is abnormal in a preset time period, the abnormal electric equipment can be rapidly determined based on the obtained energy consumption lifting situation, so that the efficiency of positioning the abnormal electric equipment when the energy consumption of the data center is abnormal is improved, the individual investigation is not needed, and the manpower and material resources are saved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the description of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for anomaly detection in a data center according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the energy consumption in one type of data according to an embodiment of the present invention;
FIG. 3 is a flow chart of steps of another method for anomaly detection in a data center according to an embodiment of the present invention;
Fig. 4 is a block diagram of an abnormality detection apparatus of a data center according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a step flow chart of an anomaly detection method of a data center according to an embodiment of the present invention is shown, where a plurality of electric devices are deployed in the data center, and the method may include the following steps:
and 101, acquiring target energy consumption information acquired for each electric equipment.
The electric device may be a device deployed in a data center and generating energy consumption, as shown in fig. 2, and may include a chiller, a humidifier, a precision air conditioner, IT devices, a PDU (Power Distribution Unit, a power distribution unit), a UPS (Uninterruptible Power Supply ), lighting and auxiliary devices, a switching device/generator, and the like.
After the power is input, the power can be respectively transmitted to different electric equipment, so that each electric equipment can normally operate.
As an example, the power input to the data center may be 24% to the chiller, 3% to the humidifier, 15% to the precision air conditioner, 47% to the IT equipment, 3% to the PDU,6% to the UPS,2% to the lighting and auxiliary equipment, 1% to the switchgear/generator.
IT equipment also emits heat during operation, so that indoor data center heat is formed, and heat output generated by operation of electric equipment can exist in the data center.
In practical application, an energy-saving system can be deployed for a data center, and the energy-saving system can comprise modules for different electric equipment, such as an intelligent air conditioner energy-saving management module for saving energy for a precise air conditioner, an intelligent wind heat movement energy-saving management module for a water chiller, a humidifier, lighting equipment and a switching device/motor, an intelligent IT equipment energy-saving management module for IT equipment, and an intelligent power distribution system energy-saving management module for UPS and PDU.
Each module in the energy-saving system can not only manage the energy consumption of the electric equipment in the running process, but also collect and store the energy consumption condition of the electric equipment in real time.
When the target energy consumption information of each electric equipment needs to be acquired, each module in the energy saving system can be inspected by running a preset program so as to acquire the target energy consumption information of each electric equipment, wherein the target energy consumption information can refer to information related to energy consumption, such as electricity consumption and the like, of each electric equipment in the process of historical running and/or current running.
Step 102, predicting the energy consumption rising and falling condition of each electric equipment in a preset time period according to the target energy consumption information.
The preset time period may refer to a future time period relative to the current time period, for example, the current time period is 00:00:00-23:59:59 of 1 day of 7 months of 2022, and the preset time period may be 00:00:00-23:59:59 of 2 days of 7 months of 2022, which is not limited by the embodiment of the present invention.
The energy consumption lifting situation can refer to the energy consumption of the electric equipment in a period of time, and the lifting proportion of the energy consumption in the previous period of time relative to the energy consumption in the previous period of time, for example, the electricity consumption in the previous period of time is 11kwh, and the electricity consumption in the previous period of time is 10kwh, so that the energy consumption lifting situation can be 10% higher.
After the target energy consumption information of each electric equipment is obtained, the energy consumption rising and falling condition of each electric equipment in a preset time period in the future can be predicted according to the target energy consumption information corresponding to each electric equipment.
Step 103, when a preset time period is reached, if the energy consumption abnormality warning information aiming at the data center is received, determining abnormal electric equipment from a plurality of electric equipment according to the energy consumption lifting condition.
After determining the energy consumption lifting condition of each electric equipment in a preset time period in the future, detecting whether the energy consumption abnormality warning information for the data center is received or not when the system time of the data center reaches the preset time period, wherein the energy consumption abnormality warning information can be generated when the total energy consumption of the data center is abnormal or when the local energy consumption of the data center is abnormal.
In practical application, the energy consumption abnormality warning information can only indicate that the total energy consumption of the data center is abnormal or the local energy consumption of the data center is abnormal, and the power consumption abnormality warning information cannot be used for knowing which electric equipment is abnormal.
Therefore, when the energy consumption abnormality warning information aiming at the data center is received, the energy consumption lifting situation of each electric equipment, which is obtained through the previous prediction, can be combined to determine the electric equipment with abnormal energy consumption.
Specifically, the electric equipment with the most energy consumption can be used as abnormal electric equipment, or the electric equipment with the most energy consumption reduction can be used as abnormal electric equipment, and after the abnormal electric equipment is determined, the abnormal electric equipment can be reported so that an administrator or an energy-saving management system can perform energy-saving management or inspection on the abnormal electric equipment.
In the embodiment of the invention, the target energy consumption information acquired for each electric equipment can be acquired first, then the energy consumption rising and falling condition of each electric equipment in a preset time period is predicted according to the target energy consumption information, and when the energy consumption abnormality warning information for the data center is received in the preset time period, the abnormal electric equipment is determined from the plurality of electric equipment according to the energy consumption rising and falling condition. According to the embodiment of the invention, the prediction of the energy consumption lifting situation of the electric equipment of the data center is realized, when the energy consumption of the data center is abnormal in a preset time period, the abnormal electric equipment can be rapidly determined based on the obtained energy consumption lifting situation, so that the efficiency of positioning the abnormal electric equipment when the energy consumption of the data center is abnormal is improved, the individual investigation is not needed, and the manpower and material resources are saved.
Referring to fig. 3, a flowchart illustrating steps of another abnormality detection method of a data center according to an embodiment of the present invention may include the steps of:
Step 301, acquiring target energy consumption information acquired for each electric equipment, wherein the target energy consumption information comprises current energy consumption information and historical energy consumption information.
When the target energy consumption information of each electric equipment needs to be acquired, each module in the energy-saving system can be inspected by running a preset program so as to acquire the target energy consumption information of each electric equipment. The historical energy consumption information can be obtained from a storage sub-module in each module, and the current historical energy consumption information can be directly obtained from sensors deployed at each electric equipment through each module.
As an example, the energy consumption information of the precision air conditioner may mainly include an amount of electricity consumed by the precision air conditioner, which may be used to reduce a temperature of a machine room of the data center for the precision air conditioner, and the reduction of the energy consumption of the precision air conditioner may reduce a PUE (Power Usage Effectiveness, power use efficiency) value of the machine room.
As another example, the energy consumption information of the chiller, the humidifier, the lighting and auxiliary equipment, and the switching device/generator may also include the amount of power consumed by the corresponding electrical equipment, the chiller, the humidifier, the lighting and auxiliary equipment, and the switching device/generator may form wind-powered heat-removal hardware in the machine room, and for the intelligent wind-powered heat-removal energy-saving management module, reducing the energy consumption of the wind-powered heat-removal hardware may reduce the PUE value of the machine room.
As another example, the energy consumption information of the IT device can also comprise the electric quantity consumed by the IT device, the CPU temperature data and the process-level server load energy consumption data percentage units of the IT device in the period can be obtained through inspection for the IT device, and the main components of the energy consumption index of the IT device in the machine room are the CPU temperature and the process-level server load of the IT device, so that the reduction of the CPU temperature and the process-level server load of the IT device can effectively reduce the PUE value of the IT device in the machine room.
As yet another example, the energy consumption information of the UPS and the PDU may also include the power consumed by the UPS and the PDU, for which the power distribution system energy consumption data of the period may be obtained through inspection. And secondly, analyzing historical power distribution system energy consumption data operation to obtain the upper period energy consumption index. The main components of the power distribution system in the machine room are UPS and PDU, so that the power consumption of the UPS and PDU in the machine room is reduced, and the PUE value of the machine room can be effectively reduced.
The PUE is Power Usage Effectiveness, is the ratio of all energy consumed by the data center to the energy consumed by the IT load, and is one of the most basic and effective indexes for evaluating the energy efficiency of the data center. The closer the PUE value is to 1, the higher the degree of greenization of one data center. When the above value exceeds 1, IT means that the data center requires additional power overhead to support IT loads. Thus, the higher the value of the PUE, the lower the overall efficiency of the data center.
Step 302, determining a first energy consumption transition probability of a plurality of electric devices in a previous time period and a second energy consumption transition probability of a plurality of electric devices in a current time period according to the historical energy consumption information and the current energy consumption information.
The first energy consumption transition probability may refer to a proportion of energy consumption of the plurality of electric devices in a previous time period relative to energy consumption transition in the previous time period, and may be represented in a transition probability matrix, for example, the first energy consumption transition probability may be [0.3, 0.7] which may represent energy consumption used by the target electric device in the previous time period, 30% of the energy consumption is transferred to the target electric device in the previous time period, 70% of the energy consumption is transferred to the data center, and other devices except the target electric device.
The second energy consumption transition probability may refer to a proportion of energy consumption of the plurality of electric devices in the current time period relative to energy consumption transition in the previous time period.
The first energy consumption transition probability can be determined according to a preset transition probability model, when the first energy consumption transition probability needs to be determined, historical energy consumption information can be input into the transition probability model preset in value, so that the first energy consumption transition probability is obtained, wherein the preset transition probability model can be obtained based on historical energy consumption data training of each electric equipment.
And meanwhile, the historical energy consumption information and the current energy consumption information can be input into a value transition probability model, so that second energy consumption transition probabilities of a plurality of electric devices in a current time period are obtained, wherein the second energy consumption transition probabilities can refer to the energy consumption of the plurality of electric devices in the current time period and are relative to the proportion of energy consumption transition in the previous time period.
As an example, a pre-set transition probability model may be derived based on a Markov chain, and the derived transition probability model may be expressed as follows:
X(k+1)=X(k)×P;
In the formula, X (k) represents a state vector of the trend analysis and prediction object at the time t=k, P represents a one-step transition probability matrix, X (k+1) represents a state vector of the trend analysis and prediction object at the time t=k+1, and a data set can be generated by adopting a two-step transition matrix.
It should be noted that, the first energy consumption transfer probability and the second energy consumption transfer probability may include the energy consumption ratio of one electric device to transfer to itself and to other electric devices, and may also include the energy consumption ratio of other electric devices to transfer to the one electric device and to other electric devices, which is not limited in the embodiment of the present invention.
Step 303, determining a third energy consumption transition probability of the plurality of electric devices in a preset time period according to the first energy consumption transition probability and the second energy consumption transition probability.
The third energy consumption transition probability may refer to a proportion of energy consumption of the plurality of electric devices in a preset time period with respect to energy consumption transition in the current time period.
After the first energy consumption transition probability and the second energy consumption transition probability are determined, third energy consumption transition probabilities of the plurality of electric devices in a future preset time period can be predicted according to the first energy consumption transition probability and the second energy consumption transition probability.
For example, the energy consumption transition probabilities of the air conditioner in the previous time period [0.3 and 0.7], the energy consumption transition probabilities of the air conditioner in the current time period [0.6 and 0.4], and the other energy consumption transition probabilities of the air conditioner in the current time period [0.3 and 0.7].
The operation obtains the probability that the energy consumption of the air conditioner in the next time period is transferred to other occurrence:
the energy consumption of the air conditioner in the next time period changes into the probability of 0.3x0.6+0.3x0.7=0.39;
the energy consumption output probability of the air conditioner in the next time period is 0.3x0.4+0.7x0.7=0.61;
Air conditioner energy consumption transition probability of next time period [0.39, 0.61].
In one embodiment of the present invention, the energy consumption increase and decrease can be predicted by the following sub-steps:
And step 11, determining the first electric quantity of each electric equipment in the current time period according to the current energy consumption information.
First, a first electric quantity of each electric equipment in a current time period can be determined from current energy consumption information.
And a sub-step 12 of predicting the second electricity consumption of each electric equipment in a preset time period according to the third energy consumption transition probability and the first electricity consumption.
After the first electric quantity is determined, the second electric quantity of each electric equipment in the preset time period can be calculated according to the third energy consumption transition probability and the first electric quantity.
For example, the electric equipment comprises A and B, the third energy consumption transition probability is [0.3 and 0.7] for the A equipment, the first electric quantity is 10kwh, the third energy consumption transition probability is [0.6 and 0.4] for the B equipment, the first electric quantity is 20kwh, the second electric quantity of the A equipment can be calculated to be 10kwh 0.3+20kwh 0.4=11 kwh, and the second electric quantity of the B equipment is 10kwh 0.7+20kwh 0.6=19 kwh.
And step 13, predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the first electric quantity and the second electric quantity.
After the second electricity consumption is determined, the energy consumption lifting condition of each electric equipment in the preset time period can be determined according to the lifting proportion of the second electricity consumption relative to the first electricity consumption.
For example, for the equipment A, the first electricity quantity is 10kwh, the second electricity quantity is 11kwh, and the energy consumption of the equipment A can be determined to be increased by 10 percent.
In practical application, the energy consumption lifting situation comprises an energy consumption lifting proportion or an energy consumption reducing proportion, and after the abnormal probability of the energy consumption of all electric equipment in a preset time period is determined, the embodiment of the invention can further comprise the following steps:
And when the energy consumption reduction ratio exceeds the second threshold, carrying out abnormal alarm prompt on the electric equipment corresponding to the energy consumption reduction ratio.
Specifically, the energy consumption rising and falling condition can indicate whether the energy consumption using condition of the electric equipment in the preset time period is normal, and when the energy consumption rising proportion of the electric equipment exceeds a first threshold value, the electric equipment can indicate that the energy consumption of the electric equipment possibly appears abnormal in the future preset time period. At this time, abnormal alarm prompt can be performed in advance for the electric equipment with the energy consumption increasing proportion exceeding the first threshold value. For example, an exception report is made for the powered device so that an administrator or energy saving system may pre-manage or check the powered device.
Or when the energy consumption reduction ratio of the electric equipment exceeds the second threshold value, the electric equipment can also indicate that the electric equipment possibly has abnormal energy consumption in a preset time period in the future, for example, the electric equipment can not work normally, so that the energy consumption is reduced.
At this time, abnormal alarm prompt can be performed in advance for the electric equipment with the energy consumption reduction ratio exceeding the second threshold value.
Step 304, when the data center includes a plurality of areas and the energy consumption abnormality warning information for the data center is received in a preset time period, determining an abnormality occurrence area from the plurality of areas according to the energy consumption abnormality warning information.
In practical application, the energy consumption abnormality warning information may be an indication that energy consumption abnormality exists in electric equipment in a certain area in the data center, and at this time, an abnormality occurrence area where energy consumption abnormality occurs may be determined from a plurality of areas in the data center according to the energy consumption abnormality warning information.
And 305, determining abnormal electric equipment from the electric equipment in the abnormal occurrence area according to the energy consumption lifting condition.
Then, one or more electrical devices in the abnormal occurrence area are determined, and then, the abnormal electrical devices can be determined based on the energy consumption rising and falling conditions of the one or more electrical devices. For example, when the energy consumption abnormality warning information indicates that the energy consumption is abnormally increased, the energy consumption lifting condition is that the energy consumption is increased in one or more electric equipment, and the electric equipment with the largest lifting value is used as the abnormal electric equipment. Or when the energy consumption abnormality warning information indicates that the energy consumption is abnormally reduced, the energy consumption is reduced in the case of the energy consumption increase in one or more electric equipment, and the electric equipment with the largest reduction value is taken as the abnormal electric equipment, which is not limited by the embodiment of the invention.
After the abnormal electric equipment is determined, the abnormal electric equipment can be reported so that an administrator or an energy-saving management system can perform energy-saving management or inspection on the abnormal electric equipment.
In an embodiment of the invention, a fusion computer (cloud operating system software) technology can be adopted to construct a virtual data center for the data center, and the virtual data center can be mapped with an energy-saving system, modules in the energy-saving system and electric equipment correspondingly managed by each module. The server of the data center can complete the interaction with the information of the virtual data center through an open api (open platform).
For each data center, the data centers can be respectively connected with a central server so as to receive a transition probability model issued by the central server, and specifically, the central server can send a flag (issuing instruction) to the corresponding server of the data center in each place. After receiving the flag, the servers in each place access the history database identification field flag deployed in the local server, check whether the transition probability model is deployed locally, wherein flag=1 indicates that the transition probability model is deployed, flag=0 indicates that the transition probability model is not deployed, and if the transition probability model is not deployed, the central server is informed to request to issue through a program sending instruction. And after receiving the request instruction, the central server sends the transition probability model to the local server.
The local server can carry out privacy data training after receiving the transition probability model, namely, the energy consumption information of each electric equipment is mapped in a history database corresponding to the obtained local virtual data center by utilizing the distributed virtual exchange characteristic of the virtual data center constructed by the fusion computer.
When the data center generates local abnormality in the energy consumption link, the identification corresponding to the abnormal electric equipment determined based on the method can be transmitted to the virtual data center through the open api, and the virtual data center manages the energy consumption of the corresponding abnormal electric equipment through the corresponding module of the mapped energy-saving system.
As an example, the energy saving system of the data center in the embodiment of the present invention may perform energy consumption control, energy saving and emission reduction on each electric device based on AI (ARTIFICIAL INTELLIGENCE ) technology, which is not limited in this embodiment of the present invention.
According to the embodiment of the invention, the target energy consumption information acquired for each electric equipment can be acquired firstly, the target energy consumption information comprises current energy consumption information and historical energy consumption information, then the first energy consumption transition probability of the plurality of electric equipment in the previous time period and the second energy consumption transition probability of the plurality of electric equipment in the current time period are determined according to the historical energy consumption information and the current energy consumption information, the third energy consumption transition probability of the plurality of electric equipment in the preset time period is determined according to the first energy consumption transition probability and the second energy consumption transition probability, the data center comprises a plurality of areas, when the energy consumption abnormality warning information for the data center is received in the preset time period, an abnormality occurrence area is determined from the plurality of areas according to the energy consumption abnormality warning information, and the abnormal electric equipment is determined from the electric equipment in the abnormality occurrence area according to the energy consumption lifting condition. According to the embodiment of the invention, the prediction of the energy consumption lifting situation of the electric equipment of the data center is realized, when the energy consumption of the data center is abnormal in a preset time period, the abnormal electric equipment can be rapidly determined based on the obtained energy consumption lifting situation, so that the efficiency of positioning the abnormal electric equipment when the energy consumption of the data center is abnormal is improved, the individual investigation is not needed, and the manpower and material resources are saved.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
Referring to fig. 4, a schematic structural diagram of an anomaly detection device of a data center according to an embodiment of the present invention is shown, where a plurality of electric devices are disposed in the data center, and the anomaly detection device may include the following modules:
An acquisition module 401, configured to acquire target energy consumption information acquired for each electric device;
The prediction module 402 is configured to predict an energy consumption lifting situation of each electric device in a preset time period according to the target energy consumption information;
And the alarm module 403 is configured to determine an abnormal electric device from the plurality of electric devices according to the energy consumption rising and falling condition if the abnormal energy consumption alarm information for the data center is received during the preset time period.
In an alternative embodiment of the present invention, the target energy consumption information includes current energy consumption information and historical energy consumption information, and the prediction module 402 includes:
The first transfer probability determining submodule is used for determining first energy consumption transfer probabilities of a plurality of electric equipment in a previous time period and second energy consumption transfer probabilities of a plurality of electric equipment in a current time period according to the historical energy consumption information and the current energy consumption information;
the second energy consumption transition probability determination submodule is used for determining third energy consumption transition probabilities of the plurality of electric equipment in a preset time period according to the first energy consumption transition probability and the second energy consumption transition probability;
and the lifting condition determining sub-module is used for predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the third energy consumption transfer probability.
In an optional embodiment of the invention, the lifting condition determining submodule is used for determining first electric quantity of each electric equipment in a current time period according to current energy consumption information, determining second electric quantity of each electric equipment in a preset time period according to third energy consumption transfer probability and the first electric quantity, and determining energy consumption lifting condition of each electric equipment in the preset time period according to the first electric quantity and the second electric quantity.
In an alternative embodiment of the present invention, the data center includes a plurality of areas, and the alarm module 403 includes:
the region determination submodule is used for determining an abnormal occurrence region from a plurality of regions according to the energy consumption abnormal alarm information;
The abnormal equipment determining submodule is used for determining abnormal electric equipment from electric equipment in an abnormal occurrence area according to the energy consumption lifting condition.
In an alternative embodiment of the present invention, the energy consumption increasing and decreasing condition includes an energy consumption increasing proportion or an energy consumption decreasing proportion, and the apparatus further includes:
the first prompting module is used for prompting abnormal alarm aiming at electric equipment corresponding to the energy consumption increasing proportion when the energy consumption increasing proportion exceeds a first threshold value;
And the second prompting module is used for prompting abnormal alarm aiming at the electric equipment corresponding to the energy consumption reduction ratio when the energy consumption reduction ratio exceeds a second threshold value.
In the embodiment of the invention, the target energy consumption information acquired for each electric equipment can be acquired first, then the energy consumption rising and falling condition of each electric equipment in a preset time period is predicted according to the target energy consumption information, and when the energy consumption abnormality warning information for the data center is received in the preset time period, the abnormal electric equipment is determined from the plurality of electric equipment according to the energy consumption rising and falling condition. According to the embodiment of the invention, the prediction of the energy consumption lifting situation of the electric equipment of the data center is realized, when the energy consumption of the data center is abnormal in a preset time period, the abnormal electric equipment can be rapidly determined based on the obtained energy consumption lifting situation, so that the efficiency of positioning the abnormal electric equipment when the energy consumption of the data center is abnormal is improved, the individual investigation is not needed, and the manpower and material resources are saved.
The embodiment of the invention also provides electronic equipment, which comprises a processor, a memory and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the abnormality detection method of the data center when being executed by the processor.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the abnormality detection method of the data center when being executed by a processor.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing describes the principles and embodiments of the present invention in detail using specific examples to facilitate understanding of the method and core ideas of the present invention, and meanwhile, to those skilled in the art, according to the ideas of the present invention, the present invention should not be construed as being limited to the above description.
Claims (8)
1. An anomaly detection method for a data center, wherein a plurality of electric devices are deployed in the data center, the method comprising:
Acquiring target energy consumption information acquired for each electric equipment;
According to the target energy consumption information, predicting the energy consumption lifting condition of each electric equipment in a preset time period;
When a preset time period is reached, if energy consumption abnormality warning information aiming at the data center is received, determining abnormal electric equipment from the plurality of electric equipment according to the energy consumption lifting condition;
The target energy consumption information comprises current energy consumption information and historical energy consumption information, and the predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the target energy consumption information comprises the following steps:
Determining a first energy consumption transition probability of the plurality of electric devices in the previous time period and a second energy consumption transition probability of the plurality of electric devices in the current time period according to the historical energy consumption information and the current energy consumption information, wherein the first energy consumption transition probability is the energy consumption of the plurality of electric devices in the previous time period, relative to the proportion of energy consumption transition in the previous time period, and the second energy consumption transition probability is the energy consumption of the plurality of electric devices in the current time period, relative to the proportion of energy consumption transition in the previous time period;
Determining a third energy consumption transition probability of the plurality of electric devices in a preset time period according to the first energy consumption transition probability and the second energy consumption transition probability, wherein the third energy consumption transition probability is the proportion of the energy consumption of the plurality of electric devices in the preset time period to the energy consumption transition in the current time period;
And predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the third energy consumption transition probability.
2. The method of claim 1, wherein the determining, according to the third energy consumption transition probability, an energy consumption lifting condition of each electric device in a preset time period includes:
determining the first electric quantity of each electric equipment in the current time period according to the current energy consumption information;
predicting a second electricity consumption of each electric equipment in a preset time period according to the third energy consumption transition probability and the first electricity quantity;
And predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the first electric quantity and the second electric quantity.
3. The method of claim 1, wherein the data center includes a plurality of zones, and wherein the determining an abnormal powered device from the plurality of powered devices based on the power consumption elevation comprises:
Determining an abnormality occurrence area from the plurality of areas according to the energy consumption abnormality warning information;
And determining abnormal electric equipment from the electric equipment in the abnormal occurrence area according to the energy consumption lifting condition.
4. The method of claim 1, wherein the power up-down condition comprises a power up-down ratio or a power down ratio, the method further comprising:
when the energy consumption increasing proportion exceeds a first threshold value, carrying out abnormal alarm prompt on electric equipment corresponding to the energy consumption increasing proportion;
Or when the energy consumption reduction ratio exceeds a second threshold, carrying out abnormal alarm prompt on the electric equipment corresponding to the energy consumption reduction ratio.
5. An anomaly detection device for a data center, wherein a plurality of electrical consumers are disposed in the data center, the device comprising:
The acquisition module is used for acquiring target energy consumption information acquired for each electric equipment;
the prediction module is used for predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the target energy consumption information;
the alarm module is used for determining abnormal electric equipment from the plurality of electric equipment according to the energy consumption lifting situation if the energy consumption abnormal alarm information aiming at the data center is received in a preset time period;
the target energy consumption information comprises current energy consumption information and historical energy consumption information, and the prediction module comprises:
A first energy consumption transition probability determining sub-module, configured to determine, according to the historical energy consumption information and the current energy consumption information, a first energy consumption transition probability of the plurality of electric devices in a previous period, and a second energy consumption transition probability of the plurality of electric devices in the current period, where the first energy consumption transition probability is a proportion of energy consumption of the plurality of electric devices in the previous period with respect to energy consumption transition in the previous period, and the second energy consumption transition probability is a proportion of energy consumption of the plurality of electric devices in the current period with respect to energy consumption transition in the previous period;
a second energy consumption transition probability determining sub-module, configured to determine a third energy consumption transition probability of the plurality of electric devices in a preset time period according to the first energy consumption transition probability and the second energy consumption transition probability, where the third energy consumption transition probability is a proportion of energy consumption of the plurality of electric devices in the preset time period to energy consumption transition in a current time period;
And the lifting condition determining sub-module is used for predicting the energy consumption lifting condition of each electric equipment in a preset time period according to the third energy consumption transition probability.
6. The apparatus of claim 5, wherein the device comprises a plurality of sensors,
The lifting condition determining submodule is used for determining first electric quantity of each electric equipment in a current time period according to the current energy consumption information, determining second electric quantity of each electric equipment in a preset time period according to the third energy consumption transition probability and the first electric quantity, and determining energy consumption lifting conditions of each electric equipment in the preset time period according to the first electric quantity and the second electric quantity.
7. An electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor implements the anomaly detection method for a data center according to any one of claims 1 to 4.
8. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, which when executed by a processor implements the anomaly detection method of the data center of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210901169.9A CN115327264B (en) | 2022-07-28 | 2022-07-28 | Abnormality detection method and device for data center, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210901169.9A CN115327264B (en) | 2022-07-28 | 2022-07-28 | Abnormality detection method and device for data center, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115327264A CN115327264A (en) | 2022-11-11 |
| CN115327264B true CN115327264B (en) | 2025-06-10 |
Family
ID=83920362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210901169.9A Active CN115327264B (en) | 2022-07-28 | 2022-07-28 | Abnormality detection method and device for data center, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115327264B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116187552A (en) * | 2023-01-20 | 2023-05-30 | 阿里云计算有限公司 | Abnormality detection method, computing device and computer storage medium |
| CN116663747B (en) * | 2023-07-19 | 2024-04-12 | 广东云下汇金科技有限公司 | Intelligent early warning method and system based on data center infrastructure |
| CN117134480B (en) * | 2023-10-26 | 2024-01-12 | 常州满旺半导体科技有限公司 | A power supply regulation monitoring system and method based on big data analysis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114200877A (en) * | 2021-11-12 | 2022-03-18 | 珠海大横琴科技发展有限公司 | Monitoring method and device for electric equipment |
| CN114495446A (en) * | 2022-01-04 | 2022-05-13 | 珠海格力电器股份有限公司 | Energy consumption monitoring alarm method and device, computing equipment and storage medium |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004679B (en) * | 2010-11-22 | 2012-07-25 | 四川大学 | Componentization embedded software energy consumption estimation model based on Markov chain |
| JP5604312B2 (en) * | 2011-01-06 | 2014-10-08 | 株式会社日立製作所 | Anomaly detection method and information processing system using the same |
| KR20130120360A (en) * | 2012-07-06 | 2013-11-04 | 주식회사 이에스윈 | Apparatus and method for controlling of power consumption appliance |
| CN104537438B (en) * | 2014-12-26 | 2018-03-02 | 国家电网公司 | A kind of prediction of peak of power consumption and monitoring method |
| CN108776276B (en) * | 2018-06-29 | 2020-11-13 | 合肥工业大学 | Power consumption abnormity detection method and system |
| CN111368290B (en) * | 2018-12-26 | 2023-06-09 | 中兴通讯股份有限公司 | A data anomaly detection method, device and terminal equipment |
| CN112418513A (en) * | 2020-11-19 | 2021-02-26 | 青岛海尔科技有限公司 | Temperature prediction method and device, storage medium, and electronic device |
| CN113341786A (en) * | 2021-04-29 | 2021-09-03 | 重庆中烟工业有限责任公司 | Equipment energy consumption control method and device and computer readable storage medium |
| CN113505935B (en) * | 2021-07-26 | 2022-06-28 | 上海东方低碳科技产业股份有限公司 | Electric power abnormal fluctuation detection and prediction calculation method based on integrated algorithm |
| CN114021841A (en) * | 2021-11-17 | 2022-02-08 | 国网四川省电力公司经济技术研究院 | Medium-and-long-term load chain-type association prediction method and device and readable storage medium |
| CN114237884A (en) * | 2021-12-10 | 2022-03-25 | 桂林理工大学 | Cloud computing data center energy consumption optimization method based on gray Markov chain |
-
2022
- 2022-07-28 CN CN202210901169.9A patent/CN115327264B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114200877A (en) * | 2021-11-12 | 2022-03-18 | 珠海大横琴科技发展有限公司 | Monitoring method and device for electric equipment |
| CN114495446A (en) * | 2022-01-04 | 2022-05-13 | 珠海格力电器股份有限公司 | Energy consumption monitoring alarm method and device, computing equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115327264A (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115327264B (en) | Abnormality detection method and device for data center, electronic equipment and medium | |
| CN104115077B (en) | Co-location electrical architecture | |
| US9310092B2 (en) | Analytics for optimizing usage of cooling subsystems | |
| US10401401B2 (en) | System and methods thereof for monitoring of energy consumption cycles | |
| WO2015106038A1 (en) | A data center infrastructure management (dcim) system comprising predictive analytics | |
| Wu et al. | Improving data center energy efficiency using a cyber-physical systems approach: integration of building information modeling and wireless sensor networks | |
| CN119446465B (en) | Intelligent hospital logistics management platform | |
| Manoharan et al. | An Intellectual Energy Device for Household Appliances Using Artificial Neural Network | |
| CN110488896A (en) | A kind of control system and its control method of building environment | |
| CN107461881B (en) | Refrigeration host energy efficiency diagnosis method and system for hospital air conditioner room | |
| CN115017006A (en) | Auxiliary energy-saving control method and system for data center | |
| US20180231603A1 (en) | Systems and Methods for Detecting Occurence of an Event in a Household Environment | |
| CN115437876A (en) | A data center management method, device, electronic equipment and storage medium | |
| CN117555266A (en) | Data center energy consumption control method and system based on accurate measurement and calculation and PUE intervention | |
| CN118381081A (en) | An adaptive energy storage device and control system | |
| CN105612484A (en) | Systems and methods for monitoring and/or controlling resources of building structures via a dashboard interface | |
| CN121052731A (en) | A smart monitoring and control system for the operation and maintenance of a cold chain system | |
| KR20130120604A (en) | Method for management of building energy for night purge, apparatus for the same | |
| CN119644844A (en) | Method and device for dynamically adjusting environmental energy consumption of machine room | |
| CN120449436A (en) | Busbar efficiency evaluation method and system based on magnetothermal stress coupling analysis | |
| CN119168123A (en) | Electric energy meter current overload prevention method, device, server and storage medium | |
| KR102606063B1 (en) | Building Automation System with failure prediction function | |
| Kosik | Data center benchmark metrics | |
| CN207148566U (en) | A kind of data center's capacity management system | |
| CN118914712A (en) | Air conditioning unit operation energy efficiency test method, tester and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |